1 @c PSPP - a program for statistical analysis.
2 @c Copyright (C) 2017, 2020 Free Software Foundation, Inc.
3 @c Permission is granted to copy, distribute and/or modify this document
4 @c under the terms of the GNU Free Documentation License, Version 1.3
5 @c or any later version published by the Free Software Foundation;
6 @c with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts.
7 @c A copy of the license is included in the section entitled "GNU
8 @c Free Documentation License".
13 This chapter documents the statistical procedures that @pspp{} supports so
17 * DESCRIPTIVES:: Descriptive statistics.
18 * FREQUENCIES:: Frequency tables.
19 * EXAMINE:: Testing data for normality.
21 * CORRELATIONS:: Correlation tables.
22 * CROSSTABS:: Crosstabulation tables.
23 * CTABLES:: Custom tables.
24 * FACTOR:: Factor analysis and Principal Components analysis.
25 * GLM:: Univariate Linear Models.
26 * LOGISTIC REGRESSION:: Bivariate Logistic Regression.
27 * MEANS:: Average values and other statistics.
28 * NPAR TESTS:: Nonparametric tests.
29 * T-TEST:: Test hypotheses about means.
30 * ONEWAY:: One way analysis of variance.
31 * QUICK CLUSTER:: K-Means clustering.
32 * RANK:: Compute rank scores.
33 * RELIABILITY:: Reliability analysis.
34 * ROC:: Receiver Operating Characteristic.
43 /VARIABLES=@var{var_list}
44 /MISSING=@{VARIABLE,LISTWISE@} @{INCLUDE,NOINCLUDE@}
45 /FORMAT=@{LABELS,NOLABELS@} @{NOINDEX,INDEX@} @{LINE,SERIAL@}
47 /STATISTICS=@{ALL,MEAN,SEMEAN,STDDEV,VARIANCE,KURTOSIS,
48 SKEWNESS,RANGE,MINIMUM,MAXIMUM,SUM,DEFAULT,
49 SESKEWNESS,SEKURTOSIS@}
50 /SORT=@{NONE,MEAN,SEMEAN,STDDEV,VARIANCE,KURTOSIS,SKEWNESS,
51 RANGE,MINIMUM,MAXIMUM,SUM,SESKEWNESS,SEKURTOSIS,NAME@}
55 The @cmd{DESCRIPTIVES} procedure reads the active dataset and outputs
56 linear descriptive statistics requested by the user. In addition, it can optionally
59 The @subcmd{VARIABLES} subcommand, which is required, specifies the list of
60 variables to be analyzed. Keyword @subcmd{VARIABLES} is optional.
62 All other subcommands are optional:
64 The @subcmd{MISSING} subcommand determines the handling of missing variables. If
65 @subcmd{INCLUDE} is set, then user-missing values are included in the
66 calculations. If @subcmd{NOINCLUDE} is set, which is the default, user-missing
67 values are excluded. If @subcmd{VARIABLE} is set, then missing values are
68 excluded on a variable by variable basis; if @subcmd{LISTWISE} is set, then
69 the entire case is excluded whenever any value in that case has a
70 system-missing or, if @subcmd{INCLUDE} is set, user-missing value.
72 The @subcmd{FORMAT} subcommand has no effect. It is accepted for
73 backward compatibility.
75 The @subcmd{SAVE} subcommand causes @cmd{DESCRIPTIVES} to calculate Z scores for all
76 the specified variables. The Z scores are saved to new variables.
77 Variable names are generated by trying first the original variable name
78 with Z prepended and truncated to a maximum of 8 characters, then the
79 names ZSC000 through ZSC999, STDZ00 through STDZ09, ZZZZ00 through
80 ZZZZ09, ZQZQ00 through ZQZQ09, in that sequence. In addition, Z score
81 variable names can be specified explicitly on @subcmd{VARIABLES} in the variable
82 list by enclosing them in parentheses after each variable.
83 When Z scores are calculated, @pspp{} ignores @cmd{TEMPORARY},
84 treating temporary transformations as permanent.
86 The @subcmd{STATISTICS} subcommand specifies the statistics to be displayed:
90 All of the statistics below.
94 Standard error of the mean.
97 @item @subcmd{VARIANCE}
99 @item @subcmd{KURTOSIS}
100 Kurtosis and standard error of the kurtosis.
101 @item @subcmd{SKEWNESS}
102 Skewness and standard error of the skewness.
112 Mean, standard deviation of the mean, minimum, maximum.
114 Standard error of the kurtosis.
116 Standard error of the skewness.
119 The @subcmd{SORT} subcommand specifies how the statistics should be sorted. Most
120 of the possible values should be self-explanatory. @subcmd{NAME} causes the
121 statistics to be sorted by name. By default, the statistics are listed
122 in the order that they are specified on the @subcmd{VARIABLES} subcommand.
123 The @subcmd{A} and @subcmd{D} settings request an ascending or descending
124 sort order, respectively.
126 @subsection Descriptives Example
128 The @file{physiology.sav} file contains various physiological data for a sample
129 of persons. Running the @cmd{DESCRIPTIVES} command on the variables @exvar{height}
130 and @exvar{temperature} with the default options allows one to see simple linear
131 statistics for these two variables. In @ref{descriptives:ex}, these variables
132 are specfied on the @subcmd{VARIABLES} subcommand and the @subcmd{SAVE} option
133 has been used, to request that Z scores be calculated.
135 After the command has completed, this example runs @cmd{DESCRIPTIVES} again, this
136 time on the @exvar{zheight} and @exvar{ztemperature} variables,
137 which are the two normalized (Z-score) variables generated by the
138 first @cmd{DESCRIPTIVES} command.
140 @float Example, descriptives:ex
141 @psppsyntax {descriptives.sps}
142 @caption {Running two @cmd{DESCRIPTIVES} commands, one with the @subcmd{SAVE} subcommand}
145 @float Screenshot, descriptives:scr
146 @psppimage {descriptives}
147 @caption {The Descriptives dialog box with two variables and Z-Scores option selected}
150 In @ref{descriptives:res}, we can see that there are 40 valid data for each of the variables
151 and no missing values. The mean average of the height and temperature is 16677.12
152 and 37.02 respectively. The descriptive statistics for temperature seem reasonable.
153 However there is a very high standard deviation for @exvar{height} and a suspiciously
154 low minimum. This is due to a data entry error in the
155 data (@pxref{Identifying incorrect data}).
157 In the second Descriptive Statistics command, one can see that the mean and standard
158 deviation of both Z score variables is 0 and 1 respectively. All Z score statistics
159 should have these properties since they are normalized versions of the original scores.
161 @float Result, descriptives:res
162 @psppoutput {descriptives}
163 @caption {Descriptives statistics including two normalized variables (Z-scores)}
172 /VARIABLES=@var{var_list}
173 /FORMAT=@{TABLE,NOTABLE,LIMIT(@var{limit})@}
174 @{AVALUE,DVALUE,AFREQ,DFREQ@}
175 /MISSING=@{EXCLUDE,INCLUDE@}
176 /STATISTICS=@{DEFAULT,MEAN,SEMEAN,MEDIAN,MODE,STDDEV,VARIANCE,
177 KURTOSIS,SKEWNESS,RANGE,MINIMUM,MAXIMUM,SUM,
178 SESKEWNESS,SEKURTOSIS,ALL,NONE@}
180 /PERCENTILES=percent@dots{}
181 /HISTOGRAM=[MINIMUM(@var{x_min})] [MAXIMUM(@var{x_max})]
182 [@{FREQ[(@var{y_max})],PERCENT[(@var{y_max})]@}] [@{NONORMAL,NORMAL@}]
183 /PIECHART=[MINIMUM(@var{x_min})] [MAXIMUM(@var{x_max})]
184 [@{FREQ,PERCENT@}] [@{NOMISSING,MISSING@}]
185 /BARCHART=[MINIMUM(@var{x_min})] [MAXIMUM(@var{x_max})]
187 /ORDER=@{ANALYSIS,VARIABLE@}
190 (These options are not currently implemented.)
195 The @cmd{FREQUENCIES} procedure outputs frequency tables for specified
197 @cmd{FREQUENCIES} can also calculate and display descriptive statistics
198 (including median and mode) and percentiles, and various graphical representations
199 of the frequency distribution.
201 The @subcmd{VARIABLES} subcommand is the only required subcommand. Specify the
202 variables to be analyzed.
204 The @subcmd{FORMAT} subcommand controls the output format. It has several
209 @subcmd{TABLE}, the default, causes a frequency table to be output for every
210 variable specified. @subcmd{NOTABLE} prevents them from being output. @subcmd{LIMIT}
211 with a numeric argument causes them to be output except when there are
212 more than the specified number of values in the table.
215 Normally frequency tables are sorted in ascending order by value. This
216 is @subcmd{AVALUE}. @subcmd{DVALUE} tables are sorted in descending order by value.
217 @subcmd{AFREQ} and @subcmd{DFREQ} tables are sorted in ascending and descending order,
218 respectively, by frequency count.
221 The @subcmd{MISSING} subcommand controls the handling of user-missing values.
222 When @subcmd{EXCLUDE}, the default, is set, user-missing values are not included
223 in frequency tables or statistics. When @subcmd{INCLUDE} is set, user-missing
224 are included. System-missing values are never included in statistics,
225 but are listed in frequency tables.
227 The available @subcmd{STATISTICS} are the same as available
228 in @cmd{DESCRIPTIVES} (@pxref{DESCRIPTIVES}), with the addition
229 of @subcmd{MEDIAN}, the data's median
230 value, and MODE, the mode. (If there are multiple modes, the smallest
231 value is reported.) By default, the mean, standard deviation of the
232 mean, minimum, and maximum are reported for each variable.
235 @subcmd{PERCENTILES} causes the specified percentiles to be reported.
236 The percentiles should be presented at a list of numbers between 0
238 The @subcmd{NTILES} subcommand causes the percentiles to be reported at the
239 boundaries of the data set divided into the specified number of ranges.
240 For instance, @subcmd{/NTILES=4} would cause quartiles to be reported.
243 The @subcmd{HISTOGRAM} subcommand causes the output to include a histogram for
244 each specified numeric variable. The X axis by default ranges from
245 the minimum to the maximum value observed in the data, but the @subcmd{MINIMUM}
246 and @subcmd{MAXIMUM} keywords can set an explicit range.
247 @footnote{The number of
248 bins is chosen according to the Freedman-Diaconis rule:
249 @math{2 \times IQR(x)n^{-1/3}}, where @math{IQR(x)} is the interquartile range of @math{x}
250 and @math{n} is the number of samples. Note that
251 @cmd{EXAMINE} uses a different algorithm to determine bin sizes.}
252 Histograms are not created for string variables.
254 Specify @subcmd{NORMAL} to superimpose a normal curve on the
258 The @subcmd{PIECHART} subcommand adds a pie chart for each variable to the data. Each
259 slice represents one value, with the size of the slice proportional to
260 the value's frequency. By default, all non-missing values are given
262 The @subcmd{MINIMUM} and @subcmd{MAXIMUM} keywords can be used to limit the
263 displayed slices to a given range of values.
264 The keyword @subcmd{NOMISSING} causes missing values to be omitted from the
265 piechart. This is the default.
266 If instead, @subcmd{MISSING} is specified, then the pie chart includes
267 a single slice representing all system missing and user-missing cases.
270 The @subcmd{BARCHART} subcommand produces a bar chart for each variable.
271 The @subcmd{MINIMUM} and @subcmd{MAXIMUM} keywords can be used to omit
272 categories whose counts which lie outside the specified limits.
273 The @subcmd{FREQ} option (default) causes the ordinate to display the frequency
274 of each category, whereas the @subcmd{PERCENT} option displays relative
277 The @subcmd{FREQ} and @subcmd{PERCENT} options on @subcmd{HISTOGRAM} and
278 @subcmd{PIECHART} are accepted but not currently honoured.
280 The @subcmd{ORDER} subcommand is accepted but ignored.
282 @subsection Frequencies Example
284 @ref{frequencies:ex} runs a frequency analysis on the @exvar{sex}
285 and @exvar{occupation} variables from the @file{personnel.sav} file.
286 This is useful to get an general idea of the way in which these nominal
287 variables are distributed.
289 @float Example, frequencies:ex
290 @psppsyntax {frequencies.sps}
291 @caption {Running frequencies on the @exvar{sex} and @exvar{occupation} variables}
294 If you are using the graphic user interface, the dialog box is set up such that
295 by default, several statistics are calculated. Some are not particularly useful
296 for categorical variables, so you may want to disable those.
298 @float Screenshot, frequencies:scr
299 @psppimage {frequencies}
300 @caption {The frequencies dialog box with the @exvar{sex} and @exvar{occupation} variables selected}
303 From @ref{frequencies:res} it is evident that there are 33 males, 21 females and
304 2 persons for whom their sex has not been entered.
306 One can also see how many of each occupation there are in the data.
307 When dealing with string variables used as nominal values, running a frequency
308 analysis is useful to detect data input entries. Notice that
309 one @exvar{occupation} value has been mistyped as ``Scrientist''. This entry should
310 be corrected, or marked as missing before using the data.
312 @float Result, frequencies:res
313 @psppoutput {frequencies}
314 @caption {The relative frequencies of @exvar{sex} and @exvar{occupation}}
321 @cindex Exploratory data analysis
322 @cindex normality, testing
326 VARIABLES= @var{var1} [@var{var2}] @dots{} [@var{varN}]
327 [BY @var{factor1} [BY @var{subfactor1}]
328 [ @var{factor2} [BY @var{subfactor2}]]
330 [ @var{factor3} [BY @var{subfactor3}]]
332 /STATISTICS=@{DESCRIPTIVES, EXTREME[(@var{n})], ALL, NONE@}
333 /PLOT=@{BOXPLOT, NPPLOT, HISTOGRAM, SPREADLEVEL[(@var{t})], ALL, NONE@}
335 /COMPARE=@{GROUPS,VARIABLES@}
336 /ID=@var{identity_variable}
338 /PERCENTILE=[@var{percentiles}]=@{HAVERAGE, WAVERAGE, ROUND, AEMPIRICAL, EMPIRICAL @}
339 /MISSING=@{LISTWISE, PAIRWISE@} [@{EXCLUDE, INCLUDE@}]
340 [@{NOREPORT,REPORT@}]
344 The @cmd{EXAMINE} command is used to perform exploratory data analysis.
345 In particular, it is useful for testing how closely a distribution follows a
346 normal distribution, and for finding outliers and extreme values.
348 The @subcmd{VARIABLES} subcommand is mandatory.
349 It specifies the dependent variables and optionally variables to use as
350 factors for the analysis.
351 Variables listed before the first @subcmd{BY} keyword (if any) are the
353 The dependent variables may optionally be followed by a list of
354 factors which tell @pspp{} how to break down the analysis for each
357 Following the dependent variables, factors may be specified.
358 The factors (if desired) should be preceded by a single @subcmd{BY} keyword.
359 The format for each factor is
361 @var{factorvar} [BY @var{subfactorvar}].
363 Each unique combination of the values of @var{factorvar} and
364 @var{subfactorvar} divide the dataset into @dfn{cells}.
365 Statistics are calculated for each cell
366 and for the entire dataset (unless @subcmd{NOTOTAL} is given).
368 The @subcmd{STATISTICS} subcommand specifies which statistics to show.
369 @subcmd{DESCRIPTIVES} produces a table showing some parametric and
370 non-parametrics statistics.
371 @subcmd{EXTREME} produces a table showing the extremities of each cell.
372 A number in parentheses, @var{n} determines
373 how many upper and lower extremities to show.
374 The default number is 5.
376 The subcommands @subcmd{TOTAL} and @subcmd{NOTOTAL} are mutually exclusive.
377 If @subcmd{TOTAL} appears, then statistics for the entire dataset
378 as well as for each cell are produced.
379 If @subcmd{NOTOTAL} appears, then statistics are produced only for the cells
380 (unless no factor variables have been given).
381 These subcommands have no effect if there have been no factor variables
387 @cindex spreadlevel plot
388 The @subcmd{PLOT} subcommand specifies which plots are to be produced if any.
389 Available plots are @subcmd{HISTOGRAM}, @subcmd{NPPLOT}, @subcmd{BOXPLOT} and
390 @subcmd{SPREADLEVEL}.
391 The first three can be used to visualise how closely each cell conforms to a
392 normal distribution, whilst the spread vs.@: level plot can be useful to visualise
393 how the variance differs between factors.
394 Boxplots show you the outliers and extreme values.
395 @footnote{@subcmd{HISTOGRAM} uses Sturges' rule to determine the number of
396 bins, as approximately @math{1 + \log2(n)}, where @math{n} is the number of samples.
397 Note that @cmd{FREQUENCIES} uses a different algorithm to find the bin size.}
399 The @subcmd{SPREADLEVEL} plot displays the interquartile range versus the
400 median. It takes an optional parameter @var{t}, which specifies how the data
401 should be transformed prior to plotting.
402 The given value @var{t} is a power to which the data are raised. For example, if
403 @var{t} is given as 2, then the square of the data is used.
404 Zero, however is a special value. If @var{t} is 0 or
405 is omitted, then data are transformed by taking its natural logarithm instead of
406 raising to the power of @var{t}.
409 When one or more plots are requested, @subcmd{EXAMINE} also performs the
410 Shapiro-Wilk test for each category.
411 There are however a number of provisos:
413 @item All weight values must be integer.
414 @item The cumulative weight value must be in the range [3, 5000]
417 The @subcmd{COMPARE} subcommand is only relevant if producing boxplots, and it is only
418 useful there is more than one dependent variable and at least one factor.
420 @subcmd{/COMPARE=GROUPS} is specified, then one plot per dependent variable is produced,
421 each of which contain boxplots for all the cells.
422 If @subcmd{/COMPARE=VARIABLES} is specified, then one plot per cell is produced,
423 each containing one boxplot per dependent variable.
424 If the @subcmd{/COMPARE} subcommand is omitted, then @pspp{} behaves as if
425 @subcmd{/COMPARE=GROUPS} were given.
427 The @subcmd{ID} subcommand is relevant only if @subcmd{/PLOT=BOXPLOT} or
428 @subcmd{/STATISTICS=EXTREME} has been given.
429 If given, it should provide the name of a variable which is to be used
430 to labels extreme values and outliers.
431 Numeric or string variables are permissible.
432 If the @subcmd{ID} subcommand is not given, then the case number is used for
435 The @subcmd{CINTERVAL} subcommand specifies the confidence interval to use in
436 calculation of the descriptives command. The default is 95%.
439 The @subcmd{PERCENTILES} subcommand specifies which percentiles are to be calculated,
440 and which algorithm to use for calculating them. The default is to
441 calculate the 5, 10, 25, 50, 75, 90, 95 percentiles using the
442 @subcmd{HAVERAGE} algorithm.
444 The @subcmd{TOTAL} and @subcmd{NOTOTAL} subcommands are mutually exclusive. If @subcmd{NOTOTAL}
445 is given and factors have been specified in the @subcmd{VARIABLES} subcommand,
446 then statistics for the unfactored dependent variables are
447 produced in addition to the factored variables. If there are no
448 factors specified then @subcmd{TOTAL} and @subcmd{NOTOTAL} have no effect.
451 The following example generates descriptive statistics and histograms for
452 two variables @var{score1} and @var{score2}.
453 Two factors are given, @i{viz}: @var{gender} and @var{gender} BY @var{culture}.
454 Therefore, the descriptives and histograms are generated for each
456 of @var{gender} @emph{and} for each distinct combination of the values
457 of @var{gender} and @var{race}.
458 Since the @subcmd{NOTOTAL} keyword is given, statistics and histograms for
459 @var{score1} and @var{score2} covering the whole dataset are not produced.
461 EXAMINE @var{score1} @var{score2} BY
463 @var{gender} BY @var{culture}
464 /STATISTICS = DESCRIPTIVES
469 Here is a second example showing how the @cmd{examine} command can be used to find extremities.
471 EXAMINE @var{height} @var{weight} BY
473 /STATISTICS = EXTREME (3)
478 In this example, we look at the height and weight of a sample of individuals and
479 how they differ between male and female.
480 A table showing the 3 largest and the 3 smallest values of @exvar{height} and
481 @exvar{weight} for each gender, and for the whole dataset as are shown.
482 In addition, the @subcmd{/PLOT} subcommand requests boxplots.
483 Because @subcmd{/COMPARE = GROUPS} was specified, boxplots for male and female are
484 shown in juxtaposed in the same graphic, allowing us to easily see the difference between
486 Since the variable @var{name} was specified on the @subcmd{ID} subcommand,
487 values of the @var{name} variable are used to label the extreme values.
490 If you specify many dependent variables or factor variables
491 for which there are many distinct values, then @cmd{EXAMINE} will produce a very
492 large quantity of output.
498 @cindex Exploratory data analysis
499 @cindex normality, testing
503 /HISTOGRAM [(NORMAL)]= @var{var}
504 /SCATTERPLOT [(BIVARIATE)] = @var{var1} WITH @var{var2} [BY @var{var3}]
505 /BAR = @{@var{summary-function}(@var{var1}) | @var{count-function}@} BY @var{var2} [BY @var{var3}]
506 [ /MISSING=@{LISTWISE, VARIABLE@} [@{EXCLUDE, INCLUDE@}] ]
507 [@{NOREPORT,REPORT@}]
511 The @cmd{GRAPH} command produces graphical plots of data. Only one of the subcommands
512 @subcmd{HISTOGRAM}, @subcmd{BAR} or @subcmd{SCATTERPLOT} can be specified, @i{i.e.} only one plot
513 can be produced per call of @cmd{GRAPH}. The @subcmd{MISSING} is optional.
516 * SCATTERPLOT:: Cartesian Plots
517 * HISTOGRAM:: Histograms
518 * BAR CHART:: Bar Charts
522 @subsection Scatterplot
525 The subcommand @subcmd{SCATTERPLOT} produces an xy plot of the
527 @cmd{GRAPH} uses the third variable @var{var3}, if specified, to determine
528 the colours and/or markers for the plot.
529 The following is an example for producing a scatterplot.
533 /SCATTERPLOT = @var{height} WITH @var{weight} BY @var{gender}.
536 This example produces a scatterplot where @var{height} is plotted versus @var{weight}. Depending
537 on the value of the @var{gender} variable, the colour of the datapoint is different. With
538 this plot it is possible to analyze gender differences for @var{height} versus @var{weight} relation.
541 @subsection Histogram
544 The subcommand @subcmd{HISTOGRAM} produces a histogram. Only one variable is allowed for
546 The keyword @subcmd{NORMAL} may be specified in parentheses, to indicate that the ideal normal curve
547 should be superimposed over the histogram.
548 For an alternative method to produce histograms @pxref{EXAMINE}. The
549 following example produces a histogram plot for the variable @var{weight}.
553 /HISTOGRAM = @var{weight}.
557 @subsection Bar Chart
560 The subcommand @subcmd{BAR} produces a bar chart.
561 This subcommand requires that a @var{count-function} be specified (with no arguments) or a @var{summary-function} with a variable @var{var1} in parentheses.
562 Following the summary or count function, the keyword @subcmd{BY} should be specified and then a catagorical variable, @var{var2}.
563 The values of the variable @var{var2} determine the labels of the bars to be plotted.
564 Optionally a second categorical variable @var{var3} may be specified in which case a clustered (grouped) bar chart is produced.
566 Valid count functions are
569 The weighted counts of the cases in each category.
571 The weighted counts of the cases in each category expressed as a percentage of the total weights of the cases.
573 The cumulative weighted counts of the cases in each category.
575 The cumulative weighted counts of the cases in each category expressed as a percentage of the total weights of the cases.
578 The summary function is applied to @var{var1} across all cases in each category.
579 The recognised summary functions are:
591 The following examples assume a dataset which is the results of a survey.
592 Each respondent has indicated annual income, their sex and city of residence.
593 One could create a bar chart showing how the mean income varies between of residents of different cities, thus:
595 GRAPH /BAR = MEAN(@var{income}) BY @var{city}.
598 This can be extended to also indicate how income in each city differs between the sexes.
600 GRAPH /BAR = MEAN(@var{income}) BY @var{city} BY @var{sex}.
603 One might also want to see how many respondents there are from each city. This can be achieved as follows:
605 GRAPH /BAR = COUNT BY @var{city}.
608 Bar charts can also be produced using the @ref{FREQUENCIES} and @ref{CROSSTABS} commands.
611 @section CORRELATIONS
616 /VARIABLES = @var{var_list} [ WITH @var{var_list} ]
621 /VARIABLES = @var{var_list} [ WITH @var{var_list} ]
622 /VARIABLES = @var{var_list} [ WITH @var{var_list} ]
625 [ /PRINT=@{TWOTAIL, ONETAIL@} @{SIG, NOSIG@} ]
626 [ /STATISTICS=DESCRIPTIVES XPROD ALL]
627 [ /MISSING=@{PAIRWISE, LISTWISE@} @{INCLUDE, EXCLUDE@} ]
631 The @cmd{CORRELATIONS} procedure produces tables of the Pearson correlation coefficient
632 for a set of variables. The significance of the coefficients are also given.
634 At least one @subcmd{VARIABLES} subcommand is required. If you specify the @subcmd{WITH}
635 keyword, then a non-square correlation table is produced.
636 The variables preceding @subcmd{WITH}, are used as the rows of the table,
637 and the variables following @subcmd{WITH} are used as the columns of the table.
638 If no @subcmd{WITH} subcommand is specified, then @cmd{CORRELATIONS} produces a
639 square, symmetrical table using all variables.
641 The @cmd{MISSING} subcommand determines the handling of missing variables.
642 If @subcmd{INCLUDE} is set, then user-missing values are included in the
643 calculations, but system-missing values are not.
644 If @subcmd{EXCLUDE} is set, which is the default, user-missing
645 values are excluded as well as system-missing values.
647 If @subcmd{LISTWISE} is set, then the entire case is excluded from analysis
648 whenever any variable specified in any @cmd{/VARIABLES} subcommand
649 contains a missing value.
650 If @subcmd{PAIRWISE} is set, then a case is considered missing only if either of the
651 values for the particular coefficient are missing.
652 The default is @subcmd{PAIRWISE}.
654 The @subcmd{PRINT} subcommand is used to control how the reported significance values are printed.
655 If the @subcmd{TWOTAIL} option is used, then a two-tailed test of significance is
656 printed. If the @subcmd{ONETAIL} option is given, then a one-tailed test is used.
657 The default is @subcmd{TWOTAIL}.
659 If the @subcmd{NOSIG} option is specified, then correlation coefficients with significance less than
660 0.05 are highlighted.
661 If @subcmd{SIG} is specified, then no highlighting is performed. This is the default.
664 The @subcmd{STATISTICS} subcommand requests additional statistics to be displayed. The keyword
665 @subcmd{DESCRIPTIVES} requests that the mean, number of non-missing cases, and the non-biased
666 estimator of the standard deviation are displayed.
667 These statistics are displayed in a separated table, for all the variables listed
668 in any @subcmd{/VARIABLES} subcommand.
669 The @subcmd{XPROD} keyword requests cross-product deviations and covariance estimators to
670 be displayed for each pair of variables.
671 The keyword @subcmd{ALL} is the union of @subcmd{DESCRIPTIVES} and @subcmd{XPROD}.
679 /TABLES=@var{var_list} BY @var{var_list} [BY @var{var_list}]@dots{}
680 /MISSING=@{TABLE,INCLUDE,REPORT@}
681 /FORMAT=@{TABLES,NOTABLES@}
683 /CELLS=@{COUNT,ROW,COLUMN,TOTAL,EXPECTED,RESIDUAL,SRESIDUAL,
684 ASRESIDUAL,ALL,NONE@}
685 /COUNT=@{ASIS,CASE,CELL@}
687 /STATISTICS=@{CHISQ,PHI,CC,LAMBDA,UC,BTAU,CTAU,RISK,GAMMA,D,
688 KAPPA,ETA,CORR,ALL,NONE@}
692 /VARIABLES=@var{var_list} (@var{low},@var{high})@dots{}
695 The @cmd{CROSSTABS} procedure displays crosstabulation
696 tables requested by the user. It can calculate several statistics for
697 each cell in the crosstabulation tables. In addition, a number of
698 statistics can be calculated for each table itself.
700 The @subcmd{TABLES} subcommand is used to specify the tables to be reported. Any
701 number of dimensions is permitted, and any number of variables per
702 dimension is allowed. The @subcmd{TABLES} subcommand may be repeated as many
703 times as needed. This is the only required subcommand in @dfn{general
706 Occasionally, one may want to invoke a special mode called @dfn{integer
707 mode}. Normally, in general mode, @pspp{} automatically determines
708 what values occur in the data. In integer mode, the user specifies the
709 range of values that the data assumes. To invoke this mode, specify the
710 @subcmd{VARIABLES} subcommand, giving a range of data values in parentheses for
711 each variable to be used on the @subcmd{TABLES} subcommand. Data values inside
712 the range are truncated to the nearest integer, then assigned to that
713 value. If values occur outside this range, they are discarded. When it
714 is present, the @subcmd{VARIABLES} subcommand must precede the @subcmd{TABLES}
717 In general mode, numeric and string variables may be specified on
718 TABLES. In integer mode, only numeric variables are allowed.
720 The @subcmd{MISSING} subcommand determines the handling of user-missing values.
721 When set to @subcmd{TABLE}, the default, missing values are dropped on a table by
722 table basis. When set to @subcmd{INCLUDE}, user-missing values are included in
723 tables and statistics. When set to @subcmd{REPORT}, which is allowed only in
724 integer mode, user-missing values are included in tables but marked with
725 a footnote and excluded from statistical calculations.
727 The @subcmd{FORMAT} subcommand controls the characteristics of the
728 crosstabulation tables to be displayed. It has a number of possible
733 @subcmd{TABLES}, the default, causes crosstabulation tables to be output.
734 @subcmd{NOTABLES}, which is equivalent to @code{CELLS=NONE}, suppresses them.
737 @subcmd{AVALUE}, the default, causes values to be sorted in ascending order.
738 @subcmd{DVALUE} asserts a descending sort order.
741 The @subcmd{CELLS} subcommand controls the contents of each cell in the displayed
742 crosstabulation table. The possible settings are:
758 Standardized residual.
760 Adjusted standardized residual.
764 Suppress cells entirely.
767 @samp{/CELLS} without any settings specified requests @subcmd{COUNT}, @subcmd{ROW},
768 @subcmd{COLUMN}, and @subcmd{TOTAL}.
769 If @subcmd{CELLS} is not specified at all then only @subcmd{COUNT}
772 By default, crosstabulation and statistics use raw case weights,
773 without rounding. Use the @subcmd{/COUNT} subcommand to perform
774 rounding: CASE rounds the weights of individual weights as cases are
775 read, CELL rounds the weights of cells within each crosstabulation
776 table after it has been constructed, and ASIS explicitly specifies the
777 default non-rounding behavior. When rounding is requested, ROUND, the
778 default, rounds to the nearest integer and TRUNCATE rounds toward
781 The @subcmd{STATISTICS} subcommand selects statistics for computation:
787 Pearson chi-square, likelihood ratio, Fisher's exact test, continuity
788 correction, linear-by-linear association.
792 Contingency coefficient.
796 Uncertainty coefficient.
812 Spearman correlation, Pearson's r.
819 Selected statistics are only calculated when appropriate for the
820 statistic. Certain statistics require tables of a particular size, and
821 some statistics are calculated only in integer mode.
823 @samp{/STATISTICS} without any settings selects CHISQ. If the
824 @subcmd{STATISTICS} subcommand is not given, no statistics are calculated.
827 The @samp{/BARCHART} subcommand produces a clustered bar chart for the first two
828 variables on each table.
829 If a table has more than two variables, the counts for the third and subsequent levels
830 are aggregated and the chart is produced as if there were only two variables.
833 @strong{Please note:} Currently the implementation of @cmd{CROSSTABS} has the
834 following limitations:
838 Significance of some symmetric and directional measures is not calculated.
840 Asymptotic standard error is not calculated for
841 Goodman and Kruskal's tau or symmetric Somers' d.
843 Approximate T is not calculated for symmetric uncertainty coefficient.
846 Fixes for any of these deficiencies would be welcomed.
848 @subsection Crosstabs Example
850 @cindex chi-square test of independence
852 A researcher wishes to know if, in an industry, a person's sex is related to
853 the person's occupation. To investigate this, she has determined that the
854 @file{personnel.sav} is a representative, randomly selected sample of persons.
855 The researcher's null hypothesis is that a person's sex has no relation to a
856 person's occupation. She uses a chi-squared test of independence to investigate
859 @float Example, crosstabs:ex
860 @psppsyntax {crosstabs.sps}
861 @caption {Running crosstabs on the @exvar{sex} and @exvar{occupation} variables}
864 The syntax in @ref{crosstabs:ex} conducts a chi-squared test of independence.
865 The line @code{/tables = occupation by sex} indicates that @exvar{occupation}
866 and @exvar{sex} are the variables to be tabulated. To do this using the @gui{}
867 you must place these variable names respectively in the @samp{Row} and
868 @samp{Column} fields as shown in @ref{crosstabs:scr}.
870 @float Screenshot, crosstabs:scr
871 @psppimage {crosstabs}
872 @caption {The Crosstabs dialog box with the @exvar{sex} and @exvar{occupation} variables selected}
875 Similarly, the @samp{Cells} button shows a dialog box to select the @code{count}
876 and @code{expected} options. All other cell options can be deselected for this
879 You would use the @samp{Format} and @samp{Statistics} buttons to select options
880 for the @subcmd{FORMAT} and @subcmd{STATISTICS} subcommands. In this example,
881 the @samp{Statistics} requires only the @samp{Chisq} option to be checked. All
882 other options should be unchecked. No special settings are required from the
883 @samp{Format} dialog.
885 As shown in @ref{crosstabs:res} @cmd{CROSSTABS} generates a contingency table
886 containing the observed count and the expected count of each sex and each
887 occupation. The expected count is the count which would be observed if the
888 null hypothesis were true.
890 The significance of the Pearson Chi-Square value is very much larger than the
891 normally accepted value of 0.05 and so one cannot reject the null hypothesis.
892 Thus the researcher must conclude that a person's sex has no relation to the
895 @float Results, crosstabs:res
896 @psppoutput {crosstabs}
897 @caption {The results of a test of independence between @exvar{sex} and @exvar{occupation}}
904 @cindex custom tables
905 @cindex tables, custom
907 @code{CTABLES} has the following overall syntax. At least one
908 @code{TABLE} subcommand is required:
912 @dots{}@i{global subcommands}@dots{}
913 [@t{/TABLE} @i{axis} [@t{BY} @i{axis} [@t{BY} @i{axis}]]
914 @dots{}@i{per-table subcommands}@dots{}]@dots{}
918 where each @i{axis} may be empty or take one of the following forms:
922 @i{variable} @t{[}@{@t{C} @math{|} @t{S}@}@t{]}
926 @i{axis} @t{(}@i{summary} [@i{string}] [@i{format}]@t{)}
929 The following subcommands precede the first @code{TABLE} subcommand
930 and apply to all of the output tables. All of these subcommands are
935 [@t{MINCOLWIDTH=}@{@t{DEFAULT} @math{|} @i{width}@}]
936 [@t{MAXCOLWIDTH=}@{@t{DEFAULT} @math{|} @i{width}@}]
937 [@t{UNITS=}@{@t{POINTS} @math{|} @t{INCHES} @math{|} @t{CM}@}]
938 [@t{EMPTY=}@{@t{ZERO} @math{|} @t{BLANK} @math{|} @i{string}@}]
939 [@t{MISSING=}@i{string}]
941 @t{VARIABLES=}@i{variables}
942 @t{DISPLAY}=@{@t{DEFAULT} @math{|} @t{NAME} @math{|} @t{LABEL} @math{|} @t{BOTH} @math{|} @t{NONE}@}
943 @t{/MRSETS COUNTDUPLICATES=}@{@t{YES} @math{|} @t{NO}@}
944 @t{/SMISSING} @{@t{VARIABLE} @math{|} @t{LISTWISE}@}
945 @t{/PCOMPUTE} @t{&}@i{category}@t{=EXPR(}@i{expression}@t{)}
946 @t{/PPROPERTIES} @t{&}@i{category}@dots{}
947 [@t{LABEL=}@i{string}]
948 [@t{FORMAT=}[@i{summary} @i{format}]@dots{}]
949 [@t{HIDESOURCECATS=}@{@t{NO} @math{|} @t{YES}@}
950 @t{/WEIGHT VARIABLE=}@i{variable}
951 @t{/HIDESMALLCOUNTS COUNT=@i{count}}
954 The following subcommands follow @code{TABLE} and apply only to the
955 previous @code{TABLE}. All of these subcommands are optional:
959 [@t{POSITION=}@{@t{COLUMN} @math{|} @t{ROW} @math{|} @t{LAYER}@}]
960 [@t{VISIBLE=}@{@t{YES} @math{|} @t{NO}@}]
961 @t{/CLABELS} @{@t{AUTO} @math{|} @{@t{ROWLABELS}@math{|}@t{COLLABELS}@}@t{=}@{@t{OPPOSITE}@math{|}@t{LAYER}@}@}
962 @t{/CRITERIA CILEVEL=}@i{percentage}
963 @t{/CATEGORIES} @t{VARIABLES=}@i{variables}
964 @{@t{[}@i{value}@t{,} @i{value}@dots{}@t{]}
965 @math{|} [@t{ORDER=}@{@t{A} @math{|} @t{D}@}]
966 [@t{KEY=}@{@t{VALUE} @math{|} @t{LABEL} @math{|} @i{summary}@t{(}@i{variable}@t{)}@}]
967 [@t{MISSING=}@{@t{EXCLUDE} @math{|} @t{INCLUDE}@}]@}
968 [@t{TOTAL=}@{@t{NO} @math{|} @t{YES}@} [@t{LABEL=}@i{string}] [@t{POSITION=}@{@t{AFTER} @math{|} @t{BEFORE}@}]]
969 [@t{EMPTY=}@{@t{INCLUDE} @math{|} @t{EXCLUDE}@}]
971 [@t{TITLE=}@i{string}@dots{}]
972 [@t{CAPTION=}@i{string}@dots{}]
973 [@t{CORNER=}@i{string}@dots{}]
974 @t{/SIGTEST TYPE=CHISQUARE}
975 [@t{ALPHA=}@i{siglevel}]
976 [@t{INCLUDEMRSETS=}@{@t{YES} @math{|} @t{NO}@}]
977 [@t{CATEGORIES=}@{@t{ALLVISIBLE} @math{|} @t{SUBTOTALS}@}]
978 @t{/COMPARETEST TYPE=}@{@t{PROP} @math{|} @t{MEAN}@}
979 [@t{ALPHA=}@i{value}[@t{,} @i{value}]]
980 [@t{ADJUST=}@{@t{BONFERRONI} @math{|} @t{BH} @math{|} @t{NONE}@}]
981 [@t{INCLUDEMRSETS=}@{@t{YES} @math{|} @t{NO}@}]
982 [@t{MEANSVARIANCE=}@{@t{ALLCATS} @math{|} @t{TESTEDCATS}@}]
983 [@t{CATEGORIES=}@{@t{ALLVISIBLE} @math{|} @t{SUBTOTALS}@}]
984 [@t{MERGE=}@{@t{NO} @math{|} @t{YES}@}]
985 [@t{STYLE=}@{@t{APA} @math{|} @t{SIMPLE}@}]
986 [@t{SHOWSIG=}@{@t{NO} @math{|} @t{YES}@}]
989 The @code{CTABLES} (aka ``custom tables'') command produces
990 multi-dimensional tables from categorical and scale data. It offers
991 many options for data summarization and formatting.
993 This section's examples use data from the 2008 (USA) National Survey
994 of Drinking and Driving Attitudes and Behaviors, a public domain data
995 set from the (USA) National Highway Traffic Administration and
996 available at @url{https://data.transportation.gov}. @pspp{} includes
997 this data set, with a slightly modified dictionary, as
998 @file{examples/nhtsa.sav}.
1004 @node CTABLES Basics
1007 The only required subcommand is @code{TABLE}, which specifies the
1008 variables to include along each axis:
1010 @t{/TABLE} @i{rows} [@t{BY} @i{columns} [@t{BY} @i{layers}]]
1013 In @code{TABLE}, each of @var{rows}, @var{columns}, and @var{layers}
1014 is either empty or an axis expression that specifies one or more
1015 variables. An axis expression that names a categorical variable
1016 divides the data into cells according to the values of that variable.
1017 When all the variables named on @code{TABLE} are categorical, by
1018 default each cell displays the number of cases that it contains, so
1019 specifying a single variable yields a frequency table:
1022 CTABLES /TABLE=AgeGroup.
1024 @psppoutput {ctables1}
1027 Specifying a row and a column categorical variable yields a
1031 CTABLES /TABLE=AgeGroup BY qns3a.
1033 @psppoutput {ctables2}
1036 The @samp{>} operator nests multiple variables on a single axis, e.g.:
1039 CTABLES /TABLE qn105ba BY AgeGroup > qns3a.
1041 @psppoutput {ctables3}
1044 The @samp{+} operator allows a single output table to include multiple
1045 data analyses. With @samp{+}, @code{CTABLES} divides the output table
1046 into multiple sections, each of which includes an analysis of the full
1047 data set. For example, the following command separately tabulates age
1048 group and driving frequency by gender:
1051 CTABLES /TABLE AgeGroup + qn1 BY qns3a.
1053 @psppoutput {ctables4}
1056 If @samp{+} and @samp{>} are used together, @samp{>} binds more
1057 tightly. Use parentheses to override operator precedence. Thus:
1060 CTABLES /TABLE qn26 + qn27 > qns3a.
1061 CTABLES /TABLE (qn26 + qn27) > qns3a.
1063 @psppoutput {ctables5}
1069 @cindex factor analysis
1070 @cindex principal components analysis
1071 @cindex principal axis factoring
1072 @cindex data reduction
1076 VARIABLES=@var{var_list},
1077 MATRIX IN (@{CORR,COV@}=@{*,@var{file_spec}@})
1080 [ /METHOD = @{CORRELATION, COVARIANCE@} ]
1082 [ /ANALYSIS=@var{var_list} ]
1084 [ /EXTRACTION=@{PC, PAF@}]
1086 [ /ROTATION=@{VARIMAX, EQUAMAX, QUARTIMAX, PROMAX[(@var{k})], NOROTATE@}]
1088 [ /PRINT=[INITIAL] [EXTRACTION] [ROTATION] [UNIVARIATE] [CORRELATION] [COVARIANCE] [DET] [KMO] [AIC] [SIG] [ALL] [DEFAULT] ]
1092 [ /FORMAT=[SORT] [BLANK(@var{n})] [DEFAULT] ]
1094 [ /CRITERIA=[FACTORS(@var{n})] [MINEIGEN(@var{l})] [ITERATE(@var{m})] [ECONVERGE (@var{delta})] [DEFAULT] ]
1096 [ /MISSING=[@{LISTWISE, PAIRWISE@}] [@{INCLUDE, EXCLUDE@}] ]
1099 The @cmd{FACTOR} command performs Factor Analysis or Principal Axis Factoring on a dataset. It may be used to find
1100 common factors in the data or for data reduction purposes.
1102 The @subcmd{VARIABLES} subcommand is required (unless the @subcmd{MATRIX IN}
1103 subcommand is used).
1104 It lists the variables which are to partake in the analysis. (The @subcmd{ANALYSIS}
1105 subcommand may optionally further limit the variables that
1106 participate; it is useful primarily in conjunction with @subcmd{MATRIX IN}.)
1108 If @subcmd{MATRIX IN} instead of @subcmd{VARIABLES} is specified, then the analysis
1109 is performed on a pre-prepared correlation or covariance matrix file instead of on
1110 individual data cases. Typically the matrix file will have been generated by
1111 @cmd{MATRIX DATA} (@pxref{MATRIX DATA}) or provided by a third party.
1112 If specified, @subcmd{MATRIX IN} must be followed by @samp{COV} or @samp{CORR},
1113 then by @samp{=} and @var{file_spec} all in parentheses.
1114 @var{file_spec} may either be an asterisk, which indicates the currently loaded
1115 dataset, or it may be a file name to be loaded. @xref{MATRIX DATA}, for the expected
1118 The @subcmd{/EXTRACTION} subcommand is used to specify the way in which factors
1119 (components) are extracted from the data.
1120 If @subcmd{PC} is specified, then Principal Components Analysis is used.
1121 If @subcmd{PAF} is specified, then Principal Axis Factoring is
1122 used. By default Principal Components Analysis is used.
1124 The @subcmd{/ROTATION} subcommand is used to specify the method by which the
1125 extracted solution is rotated. Three orthogonal rotation methods are available:
1126 @subcmd{VARIMAX} (which is the default), @subcmd{EQUAMAX}, and @subcmd{QUARTIMAX}.
1127 There is one oblique rotation method, @i{viz}: @subcmd{PROMAX}.
1128 Optionally you may enter the power of the promax rotation @var{k}, which must be enclosed in parentheses.
1129 The default value of @var{k} is 5.
1130 If you don't want any rotation to be performed, the word @subcmd{NOROTATE}
1131 prevents the command from performing any rotation on the data.
1133 The @subcmd{/METHOD} subcommand should be used to determine whether the
1134 covariance matrix or the correlation matrix of the data is
1135 to be analysed. By default, the correlation matrix is analysed.
1137 The @subcmd{/PRINT} subcommand may be used to select which features of the analysis are reported:
1140 @item @subcmd{UNIVARIATE}
1141 A table of mean values, standard deviations and total weights are printed.
1142 @item @subcmd{INITIAL}
1143 Initial communalities and eigenvalues are printed.
1144 @item @subcmd{EXTRACTION}
1145 Extracted communalities and eigenvalues are printed.
1146 @item @subcmd{ROTATION}
1147 Rotated communalities and eigenvalues are printed.
1148 @item @subcmd{CORRELATION}
1149 The correlation matrix is printed.
1150 @item @subcmd{COVARIANCE}
1151 The covariance matrix is printed.
1153 The determinant of the correlation or covariance matrix is printed.
1155 The anti-image covariance and anti-image correlation matrices are printed.
1157 The Kaiser-Meyer-Olkin measure of sampling adequacy and the Bartlett test of sphericity is printed.
1159 The significance of the elements of correlation matrix is printed.
1161 All of the above are printed.
1162 @item @subcmd{DEFAULT}
1163 Identical to @subcmd{INITIAL} and @subcmd{EXTRACTION}.
1166 If @subcmd{/PLOT=EIGEN} is given, then a ``Scree'' plot of the eigenvalues is
1167 printed. This can be useful for visualizing the factors and deciding
1168 which factors (components) should be retained.
1170 The @subcmd{/FORMAT} subcommand determined how data are to be
1171 displayed in loading matrices. If @subcmd{SORT} is specified, then
1172 the variables are sorted in descending order of significance. If
1173 @subcmd{BLANK(@var{n})} is specified, then coefficients whose absolute
1174 value is less than @var{n} are not printed. If the keyword
1175 @subcmd{DEFAULT} is specified, or if no @subcmd{/FORMAT} subcommand is
1176 specified, then no sorting is performed, and all coefficients are printed.
1178 You can use the @subcmd{/CRITERIA} subcommand to specify how the number of
1179 extracted factors (components) are chosen. If @subcmd{FACTORS(@var{n})} is
1180 specified, where @var{n} is an integer, then @var{n} factors are
1181 extracted. Otherwise, the @subcmd{MINEIGEN} setting is used.
1182 @subcmd{MINEIGEN(@var{l})} requests that all factors whose eigenvalues
1183 are greater than or equal to @var{l} are extracted. The default value
1184 of @var{l} is 1. The @subcmd{ECONVERGE} setting has effect only when
1185 using iterative algorithms for factor extraction (such as Principal Axis
1186 Factoring). @subcmd{ECONVERGE(@var{delta})} specifies that
1187 iteration should cease when the maximum absolute value of the
1188 communality estimate between one iteration and the previous is less
1189 than @var{delta}. The default value of @var{delta} is 0.001.
1191 The @subcmd{ITERATE(@var{m})} may appear any number of times and is
1192 used for two different purposes. It is used to set the maximum number
1193 of iterations (@var{m}) for convergence and also to set the maximum
1194 number of iterations for rotation.
1195 Whether it affects convergence or rotation depends upon which
1196 subcommand follows the @subcmd{ITERATE} subcommand.
1197 If @subcmd{EXTRACTION} follows, it affects convergence.
1198 If @subcmd{ROTATION} follows, it affects rotation.
1199 If neither @subcmd{ROTATION} nor @subcmd{EXTRACTION} follow a
1200 @subcmd{ITERATE} subcommand, then the entire subcommand is ignored.
1201 The default value of @var{m} is 25.
1203 The @cmd{MISSING} subcommand determines the handling of missing
1204 variables. If @subcmd{INCLUDE} is set, then user-missing values are
1205 included in the calculations, but system-missing values are not.
1206 If @subcmd{EXCLUDE} is set, which is the default, user-missing
1207 values are excluded as well as system-missing values. This is the
1208 default. If @subcmd{LISTWISE} is set, then the entire case is excluded
1209 from analysis whenever any variable specified in the @cmd{VARIABLES}
1210 subcommand contains a missing value.
1212 If @subcmd{PAIRWISE} is set, then a case is considered missing only if
1213 either of the values for the particular coefficient are missing.
1214 The default is @subcmd{LISTWISE}.
1220 @cindex univariate analysis of variance
1221 @cindex fixed effects
1222 @cindex factorial anova
1223 @cindex analysis of variance
1228 GLM @var{dependent_vars} BY @var{fixed_factors}
1229 [/METHOD = SSTYPE(@var{type})]
1230 [/DESIGN = @var{interaction_0} [@var{interaction_1} [... @var{interaction_n}]]]
1231 [/INTERCEPT = @{INCLUDE|EXCLUDE@}]
1232 [/MISSING = @{INCLUDE|EXCLUDE@}]
1235 The @cmd{GLM} procedure can be used for fixed effects factorial Anova.
1237 The @var{dependent_vars} are the variables to be analysed.
1238 You may analyse several variables in the same command in which case they should all
1239 appear before the @code{BY} keyword.
1241 The @var{fixed_factors} list must be one or more categorical variables. Normally it
1242 does not make sense to enter a scalar variable in the @var{fixed_factors} and doing
1243 so may cause @pspp{} to do a lot of unnecessary processing.
1245 The @subcmd{METHOD} subcommand is used to change the method for producing the sums of
1246 squares. Available values of @var{type} are 1, 2 and 3. The default is type 3.
1248 You may specify a custom design using the @subcmd{DESIGN} subcommand.
1249 The design comprises a list of interactions where each interaction is a
1250 list of variables separated by a @samp{*}. For example the command
1252 GLM subject BY sex age_group race
1253 /DESIGN = age_group sex group age_group*sex age_group*race
1255 @noindent specifies the model @math{subject = age_group + sex + race + age_group*sex + age_group*race}.
1256 If no @subcmd{DESIGN} subcommand is specified, then the default is all possible combinations
1257 of the fixed factors. That is to say
1259 GLM subject BY sex age_group race
1262 @math{subject = age_group + sex + race + age_group*sex + age_group*race + sex*race + age_group*sex*race}.
1265 The @subcmd{MISSING} subcommand determines the handling of missing
1267 If @subcmd{INCLUDE} is set then, for the purposes of GLM analysis,
1268 only system-missing values are considered
1269 to be missing; user-missing values are not regarded as missing.
1270 If @subcmd{EXCLUDE} is set, which is the default, then user-missing
1271 values are considered to be missing as well as system-missing values.
1272 A case for which any dependent variable or any factor
1273 variable has a missing value is excluded from the analysis.
1275 @node LOGISTIC REGRESSION
1276 @section LOGISTIC REGRESSION
1278 @vindex LOGISTIC REGRESSION
1279 @cindex logistic regression
1280 @cindex bivariate logistic regression
1283 LOGISTIC REGRESSION [VARIABLES =] @var{dependent_var} WITH @var{predictors}
1285 [/CATEGORICAL = @var{categorical_predictors}]
1287 [@{/NOCONST | /ORIGIN | /NOORIGIN @}]
1289 [/PRINT = [SUMMARY] [DEFAULT] [CI(@var{confidence})] [ALL]]
1291 [/CRITERIA = [BCON(@var{min_delta})] [ITERATE(@var{max_interations})]
1292 [LCON(@var{min_likelihood_delta})] [EPS(@var{min_epsilon})]
1293 [CUT(@var{cut_point})]]
1295 [/MISSING = @{INCLUDE|EXCLUDE@}]
1298 Bivariate Logistic Regression is used when you want to explain a dichotomous dependent
1299 variable in terms of one or more predictor variables.
1301 The minimum command is
1303 LOGISTIC REGRESSION @var{y} WITH @var{x1} @var{x2} @dots{} @var{xn}.
1305 Here, @var{y} is the dependent variable, which must be dichotomous and @var{x1} @dots{} @var{xn}
1306 are the predictor variables whose coefficients the procedure estimates.
1308 By default, a constant term is included in the model.
1309 Hence, the full model is
1312 = b_0 + b_1 {\bf x_1}
1318 Predictor variables which are categorical in nature should be listed on the @subcmd{/CATEGORICAL} subcommand.
1319 Simple variables as well as interactions between variables may be listed here.
1321 If you want a model without the constant term @math{b_0}, use the keyword @subcmd{/ORIGIN}.
1322 @subcmd{/NOCONST} is a synonym for @subcmd{/ORIGIN}.
1324 An iterative Newton-Raphson procedure is used to fit the model.
1325 The @subcmd{/CRITERIA} subcommand is used to specify the stopping criteria of the procedure,
1326 and other parameters.
1327 The value of @var{cut_point} is used in the classification table. It is the
1328 threshold above which predicted values are considered to be 1. Values
1329 of @var{cut_point} must lie in the range [0,1].
1330 During iterations, if any one of the stopping criteria are satisfied, the procedure is
1331 considered complete.
1332 The stopping criteria are:
1334 @item The number of iterations exceeds @var{max_iterations}.
1335 The default value of @var{max_iterations} is 20.
1336 @item The change in the all coefficient estimates are less than @var{min_delta}.
1337 The default value of @var{min_delta} is 0.001.
1338 @item The magnitude of change in the likelihood estimate is less than @var{min_likelihood_delta}.
1339 The default value of @var{min_delta} is zero.
1340 This means that this criterion is disabled.
1341 @item The differential of the estimated probability for all cases is less than @var{min_epsilon}.
1342 In other words, the probabilities are close to zero or one.
1343 The default value of @var{min_epsilon} is 0.00000001.
1347 The @subcmd{PRINT} subcommand controls the display of optional statistics.
1348 Currently there is one such option, @subcmd{CI}, which indicates that the
1349 confidence interval of the odds ratio should be displayed as well as its value.
1350 @subcmd{CI} should be followed by an integer in parentheses, to indicate the
1351 confidence level of the desired confidence interval.
1353 The @subcmd{MISSING} subcommand determines the handling of missing
1355 If @subcmd{INCLUDE} is set, then user-missing values are included in the
1356 calculations, but system-missing values are not.
1357 If @subcmd{EXCLUDE} is set, which is the default, user-missing
1358 values are excluded as well as system-missing values.
1359 This is the default.
1370 [ BY @{@var{var_list}@} [BY @{@var{var_list}@} [BY @{@var{var_list}@} @dots{} ]]]
1372 [ /@{@var{var_list}@}
1373 [ BY @{@var{var_list}@} [BY @{@var{var_list}@} [BY @{@var{var_list}@} @dots{} ]]] ]
1375 [/CELLS = [MEAN] [COUNT] [STDDEV] [SEMEAN] [SUM] [MIN] [MAX] [RANGE]
1376 [VARIANCE] [KURT] [SEKURT]
1377 [SKEW] [SESKEW] [FIRST] [LAST]
1378 [HARMONIC] [GEOMETRIC]
1383 [/MISSING = [INCLUDE] [DEPENDENT]]
1386 You can use the @cmd{MEANS} command to calculate the arithmetic mean and similar
1387 statistics, either for the dataset as a whole or for categories of data.
1389 The simplest form of the command is
1393 @noindent which calculates the mean, count and standard deviation for @var{v}.
1394 If you specify a grouping variable, for example
1396 MEANS @var{v} BY @var{g}.
1398 @noindent then the means, counts and standard deviations for @var{v} after having
1399 been grouped by @var{g} are calculated.
1400 Instead of the mean, count and standard deviation, you could specify the statistics
1401 in which you are interested:
1403 MEANS @var{x} @var{y} BY @var{g}
1404 /CELLS = HARMONIC SUM MIN.
1406 This example calculates the harmonic mean, the sum and the minimum values of @var{x} and @var{y}
1409 The @subcmd{CELLS} subcommand specifies which statistics to calculate. The available statistics
1413 @cindex arithmetic mean
1414 The arithmetic mean.
1415 @item @subcmd{COUNT}
1416 The count of the values.
1417 @item @subcmd{STDDEV}
1418 The standard deviation.
1419 @item @subcmd{SEMEAN}
1420 The standard error of the mean.
1422 The sum of the values.
1427 @item @subcmd{RANGE}
1428 The difference between the maximum and minimum values.
1429 @item @subcmd{VARIANCE}
1431 @item @subcmd{FIRST}
1432 The first value in the category.
1434 The last value in the category.
1437 @item @subcmd{SESKEW}
1438 The standard error of the skewness.
1441 @item @subcmd{SEKURT}
1442 The standard error of the kurtosis.
1443 @item @subcmd{HARMONIC}
1444 @cindex harmonic mean
1446 @item @subcmd{GEOMETRIC}
1447 @cindex geometric mean
1451 In addition, three special keywords are recognized:
1453 @item @subcmd{DEFAULT}
1454 This is the same as @subcmd{MEAN} @subcmd{COUNT} @subcmd{STDDEV}.
1456 All of the above statistics are calculated.
1458 No statistics are calculated (only a summary is shown).
1462 More than one @dfn{table} can be specified in a single command.
1463 Each table is separated by a @samp{/}. For
1467 @var{c} @var{d} @var{e} BY @var{x}
1468 /@var{a} @var{b} BY @var{x} @var{y}
1469 /@var{f} BY @var{y} BY @var{z}.
1471 has three tables (the @samp{TABLE =} is optional).
1472 The first table has three dependent variables @var{c}, @var{d} and @var{e}
1473 and a single categorical variable @var{x}.
1474 The second table has two dependent variables @var{a} and @var{b},
1475 and two categorical variables @var{x} and @var{y}.
1476 The third table has a single dependent variables @var{f}
1477 and a categorical variable formed by the combination of @var{y} and @var{z}.
1480 By default values are omitted from the analysis only if missing values
1481 (either system missing or user missing)
1482 for any of the variables directly involved in their calculation are
1484 This behaviour can be modified with the @subcmd{/MISSING} subcommand.
1485 Three options are possible: @subcmd{TABLE}, @subcmd{INCLUDE} and @subcmd{DEPENDENT}.
1487 @subcmd{/MISSING = INCLUDE} says that user missing values, either in the dependent
1488 variables or in the categorical variables should be taken at their face
1489 value, and not excluded.
1491 @subcmd{/MISSING = DEPENDENT} says that user missing values, in the dependent
1492 variables should be taken at their face value, however cases which
1493 have user missing values for the categorical variables should be omitted
1494 from the calculation.
1496 @subsection Example Means
1498 The dataset in @file{repairs.sav} contains the mean time between failures (@exvar{mtbf})
1499 for a sample of artifacts produced by different factories and trialed under
1500 different operating conditions.
1501 Since there are four combinations of categorical variables, by simply looking
1502 at the list of data, it would be hard to how the scores vary for each category.
1503 @ref{means:ex} shows one way of tabulating the @exvar{mtbf} in a way which is
1504 easier to understand.
1506 @float Example, means:ex
1507 @psppsyntax {means.sps}
1508 @caption {Running @cmd{MEANS} on the @exvar{mtbf} score with categories @exvar{factory} and @exvar{environment}}
1511 The results are shown in @ref{means:res}. The figures shown indicate the mean,
1512 standard deviation and number of samples in each category.
1513 These figures however do not indicate whether the results are statistically
1514 significant. For that, you would need to use the procedures @cmd{ONEWAY}, @cmd{GLM} or
1515 @cmd{T-TEST} depending on the hypothesis being tested.
1517 @float Result, means:res
1519 @caption {The @exvar{mtbf} categorised by @exvar{factory} and @exvar{environment}}
1522 Note that there is no limit to the number of variables for which you can calculate
1523 statistics, nor to the number of categorical variables per layer, nor the number
1525 However, running @cmd{MEANS} on a large numbers of variables, or with categorical variables
1526 containing a large number of distinct values may result in an extremely large output, which
1527 will not be easy to interpret.
1528 So you should consider carefully which variables to select for participation in the analysis.
1534 @cindex nonparametric tests
1539 nonparametric test subcommands
1544 [ /STATISTICS=@{DESCRIPTIVES@} ]
1546 [ /MISSING=@{ANALYSIS, LISTWISE@} @{INCLUDE, EXCLUDE@} ]
1548 [ /METHOD=EXACT [ TIMER [(@var{n})] ] ]
1551 @cmd{NPAR TESTS} performs nonparametric tests.
1552 Non parametric tests make very few assumptions about the distribution of the
1554 One or more tests may be specified by using the corresponding subcommand.
1555 If the @subcmd{/STATISTICS} subcommand is also specified, then summary statistics are
1556 produces for each variable that is the subject of any test.
1558 Certain tests may take a long time to execute, if an exact figure is required.
1559 Therefore, by default asymptotic approximations are used unless the
1560 subcommand @subcmd{/METHOD=EXACT} is specified.
1561 Exact tests give more accurate results, but may take an unacceptably long
1562 time to perform. If the @subcmd{TIMER} keyword is used, it sets a maximum time,
1563 after which the test is abandoned, and a warning message printed.
1564 The time, in minutes, should be specified in parentheses after the @subcmd{TIMER} keyword.
1565 If the @subcmd{TIMER} keyword is given without this figure, then a default value of 5 minutes
1570 * BINOMIAL:: Binomial Test
1571 * CHISQUARE:: Chi-square Test
1572 * COCHRAN:: Cochran Q Test
1573 * FRIEDMAN:: Friedman Test
1574 * KENDALL:: Kendall's W Test
1575 * KOLMOGOROV-SMIRNOV:: Kolmogorov Smirnov Test
1576 * KRUSKAL-WALLIS:: Kruskal-Wallis Test
1577 * MANN-WHITNEY:: Mann Whitney U Test
1578 * MCNEMAR:: McNemar Test
1579 * MEDIAN:: Median Test
1581 * SIGN:: The Sign Test
1582 * WILCOXON:: Wilcoxon Signed Ranks Test
1587 @subsection Binomial test
1589 @cindex binomial test
1592 [ /BINOMIAL[(@var{p})]=@var{var_list}[(@var{value1}[, @var{value2})] ] ]
1595 The @subcmd{/BINOMIAL} subcommand compares the observed distribution of a dichotomous
1596 variable with that of a binomial distribution.
1597 The variable @var{p} specifies the test proportion of the binomial
1599 The default value of 0.5 is assumed if @var{p} is omitted.
1601 If a single value appears after the variable list, then that value is
1602 used as the threshold to partition the observed values. Values less
1603 than or equal to the threshold value form the first category. Values
1604 greater than the threshold form the second category.
1606 If two values appear after the variable list, then they are used
1607 as the values which a variable must take to be in the respective
1609 Cases for which a variable takes a value equal to neither of the specified
1610 values, take no part in the test for that variable.
1612 If no values appear, then the variable must assume dichotomous
1614 If more than two distinct, non-missing values for a variable
1615 under test are encountered then an error occurs.
1617 If the test proportion is equal to 0.5, then a two tailed test is
1618 reported. For any other test proportion, a one tailed test is
1620 For one tailed tests, if the test proportion is less than
1621 or equal to the observed proportion, then the significance of
1622 observing the observed proportion or more is reported.
1623 If the test proportion is more than the observed proportion, then the
1624 significance of observing the observed proportion or less is reported.
1625 That is to say, the test is always performed in the observed
1628 @pspp{} uses a very precise approximation to the gamma function to
1629 compute the binomial significance. Thus, exact results are reported
1630 even for very large sample sizes.
1634 @subsection Chi-square Test
1636 @cindex chi-square test
1640 [ /CHISQUARE=@var{var_list}[(@var{lo},@var{hi})] [/EXPECTED=@{EQUAL|@var{f1}, @var{f2} @dots{} @var{fn}@}] ]
1644 The @subcmd{/CHISQUARE} subcommand produces a chi-square statistic for the differences
1645 between the expected and observed frequencies of the categories of a variable.
1646 Optionally, a range of values may appear after the variable list.
1647 If a range is given, then non integer values are truncated, and values
1648 outside the specified range are excluded from the analysis.
1650 The @subcmd{/EXPECTED} subcommand specifies the expected values of each
1652 There must be exactly one non-zero expected value, for each observed
1653 category, or the @subcmd{EQUAL} keyword must be specified.
1654 You may use the notation @subcmd{@var{n}*@var{f}} to specify @var{n}
1655 consecutive expected categories all taking a frequency of @var{f}.
1656 The frequencies given are proportions, not absolute frequencies. The
1657 sum of the frequencies need not be 1.
1658 If no @subcmd{/EXPECTED} subcommand is given, then equal frequencies
1661 @subsubsection Chi-square Example
1663 A researcher wishes to investigate whether there are an equal number of
1664 persons of each sex in a population. The sample chosen for invesigation
1665 is that from the @file {physiology.sav} dataset. The null hypothesis for
1666 the test is that the population comprises an equal number of males and females.
1667 The analysis is performed as shown in @ref{chisquare:ex}.
1669 @float Example, chisquare:ex
1670 @psppsyntax {chisquare.sps}
1671 @caption {Performing a chi-square test to check for equal distribution of sexes}
1674 There is only one test variable, @i{viz:} @exvar{sex}. The other variables in the dataset
1677 @float Screenshot, chisquare:scr
1678 @psppimage {chisquare}
1679 @caption {Performing a chi-square test using the graphic user interface}
1682 In @ref{chisquare:res} the summary box shows that in the sample, there are more males
1683 than females. However the significance of chi-square result is greater than 0.05
1684 --- the most commonly accepted p-value --- and therefore
1685 there is not enough evidence to reject the null hypothesis and one must conclude
1686 that the evidence does not indicate that there is an imbalance of the sexes
1689 @float Result, chisquare:res
1690 @psppoutput {chisquare}
1691 @caption {The results of running a chi-square test on @exvar{sex}}
1696 @subsection Cochran Q Test
1698 @cindex Cochran Q test
1699 @cindex Q, Cochran Q
1702 [ /COCHRAN = @var{var_list} ]
1705 The Cochran Q test is used to test for differences between three or more groups.
1706 The data for @var{var_list} in all cases must assume exactly two
1707 distinct values (other than missing values).
1709 The value of Q is displayed along with its Asymptotic significance
1710 based on a chi-square distribution.
1713 @subsection Friedman Test
1715 @cindex Friedman test
1718 [ /FRIEDMAN = @var{var_list} ]
1721 The Friedman test is used to test for differences between repeated measures when
1722 there is no indication that the distributions are normally distributed.
1724 A list of variables which contain the measured data must be given. The procedure
1725 prints the sum of ranks for each variable, the test statistic and its significance.
1728 @subsection Kendall's W Test
1730 @cindex Kendall's W test
1731 @cindex coefficient of concordance
1734 [ /KENDALL = @var{var_list} ]
1737 The Kendall test investigates whether an arbitrary number of related samples come from the
1739 It is identical to the Friedman test except that the additional statistic W, Kendall's Coefficient of Concordance is printed.
1740 It has the range [0,1] --- a value of zero indicates no agreement between the samples whereas a value of
1741 unity indicates complete agreement.
1744 @node KOLMOGOROV-SMIRNOV
1745 @subsection Kolmogorov-Smirnov Test
1746 @vindex KOLMOGOROV-SMIRNOV
1748 @cindex Kolmogorov-Smirnov test
1751 [ /KOLMOGOROV-SMIRNOV (@{NORMAL [@var{mu}, @var{sigma}], UNIFORM [@var{min}, @var{max}], POISSON [@var{lambda}], EXPONENTIAL [@var{scale}] @}) = @var{var_list} ]
1754 The one sample Kolmogorov-Smirnov subcommand is used to test whether or not a dataset is
1755 drawn from a particular distribution. Four distributions are supported, @i{viz:}
1756 Normal, Uniform, Poisson and Exponential.
1758 Ideally you should provide the parameters of the distribution against
1759 which you wish to test the data. For example, with the normal
1760 distribution the mean (@var{mu})and standard deviation (@var{sigma})
1761 should be given; with the uniform distribution, the minimum
1762 (@var{min})and maximum (@var{max}) value should be provided.
1763 However, if the parameters are omitted they are imputed from the
1764 data. Imputing the parameters reduces the power of the test so should
1765 be avoided if possible.
1767 In the following example, two variables @var{score} and @var{age} are
1768 tested to see if they follow a normal distribution with a mean of 3.5
1769 and a standard deviation of 2.0.
1772 /KOLMOGOROV-SMIRNOV (normal 3.5 2.0) = @var{score} @var{age}.
1774 If the variables need to be tested against different distributions, then a separate
1775 subcommand must be used. For example the following syntax tests @var{score} against
1776 a normal distribution with mean of 3.5 and standard deviation of 2.0 whilst @var{age}
1777 is tested against a normal distribution of mean 40 and standard deviation 1.5.
1780 /KOLMOGOROV-SMIRNOV (normal 3.5 2.0) = @var{score}
1781 /KOLMOGOROV-SMIRNOV (normal 40 1.5) = @var{age}.
1784 The abbreviated subcommand @subcmd{K-S} may be used in place of @subcmd{KOLMOGOROV-SMIRNOV}.
1786 @node KRUSKAL-WALLIS
1787 @subsection Kruskal-Wallis Test
1788 @vindex KRUSKAL-WALLIS
1790 @cindex Kruskal-Wallis test
1793 [ /KRUSKAL-WALLIS = @var{var_list} BY var (@var{lower}, @var{upper}) ]
1796 The Kruskal-Wallis test is used to compare data from an
1797 arbitrary number of populations. It does not assume normality.
1798 The data to be compared are specified by @var{var_list}.
1799 The categorical variable determining the groups to which the
1800 data belongs is given by @var{var}. The limits @var{lower} and
1801 @var{upper} specify the valid range of @var{var}.
1802 If @var{upper} is smaller than @var{lower}, the PSPP will assume their values
1803 to be reversed. Any cases for which @var{var} falls outside
1804 [@var{lower}, @var{upper}] are ignored.
1806 The mean rank of each group as well as the chi-squared value and
1807 significance of the test are printed.
1808 The abbreviated subcommand @subcmd{K-W} may be used in place of
1809 @subcmd{KRUSKAL-WALLIS}.
1813 @subsection Mann-Whitney U Test
1814 @vindex MANN-WHITNEY
1816 @cindex Mann-Whitney U test
1817 @cindex U, Mann-Whitney U
1820 [ /MANN-WHITNEY = @var{var_list} BY var (@var{group1}, @var{group2}) ]
1823 The Mann-Whitney subcommand is used to test whether two groups of data
1824 come from different populations. The variables to be tested should be
1825 specified in @var{var_list} and the grouping variable, that determines
1826 to which group the test variables belong, in @var{var}.
1827 @var{Var} may be either a string or an alpha variable.
1828 @var{Group1} and @var{group2} specify the
1829 two values of @var{var} which determine the groups of the test data.
1830 Cases for which the @var{var} value is neither @var{group1} or
1831 @var{group2} are ignored.
1833 The value of the Mann-Whitney U statistic, the Wilcoxon W, and the
1834 significance are printed.
1835 You may abbreviated the subcommand @subcmd{MANN-WHITNEY} to
1840 @subsection McNemar Test
1842 @cindex McNemar test
1845 [ /MCNEMAR @var{var_list} [ WITH @var{var_list} [ (PAIRED) ]]]
1848 Use McNemar's test to analyse the significance of the difference between
1849 pairs of correlated proportions.
1851 If the @code{WITH} keyword is omitted, then tests for all
1852 combinations of the listed variables are performed.
1853 If the @code{WITH} keyword is given, and the @code{(PAIRED)} keyword
1854 is also given, then the number of variables preceding @code{WITH}
1855 must be the same as the number following it.
1856 In this case, tests for each respective pair of variables are
1858 If the @code{WITH} keyword is given, but the
1859 @code{(PAIRED)} keyword is omitted, then tests for each combination
1860 of variable preceding @code{WITH} against variable following
1861 @code{WITH} are performed.
1863 The data in each variable must be dichotomous. If there are more
1864 than two distinct variables an error will occur and the test will
1868 @subsection Median Test
1873 [ /MEDIAN [(@var{value})] = @var{var_list} BY @var{variable} (@var{value1}, @var{value2}) ]
1876 The median test is used to test whether independent samples come from
1877 populations with a common median.
1878 The median of the populations against which the samples are to be tested
1879 may be given in parentheses immediately after the
1880 @subcmd{/MEDIAN} subcommand. If it is not given, the median is imputed from the
1881 union of all the samples.
1883 The variables of the samples to be tested should immediately follow the @samp{=} sign. The
1884 keyword @code{BY} must come next, and then the grouping variable. Two values
1885 in parentheses should follow. If the first value is greater than the second,
1886 then a 2 sample test is performed using these two values to determine the groups.
1887 If however, the first variable is less than the second, then a @i{k} sample test is
1888 conducted and the group values used are all values encountered which lie in the
1889 range [@var{value1},@var{value2}].
1893 @subsection Runs Test
1898 [ /RUNS (@{MEAN, MEDIAN, MODE, @var{value}@}) = @var{var_list} ]
1901 The @subcmd{/RUNS} subcommand tests whether a data sequence is randomly ordered.
1903 It works by examining the number of times a variable's value crosses a given threshold.
1904 The desired threshold must be specified within parentheses.
1905 It may either be specified as a number or as one of @subcmd{MEAN}, @subcmd{MEDIAN} or @subcmd{MODE}.
1906 Following the threshold specification comes the list of variables whose values are to be
1909 The subcommand shows the number of runs, the asymptotic significance based on the
1913 @subsection Sign Test
1918 [ /SIGN @var{var_list} [ WITH @var{var_list} [ (PAIRED) ]]]
1921 The @subcmd{/SIGN} subcommand tests for differences between medians of the
1923 The test does not make any assumptions about the
1924 distribution of the data.
1926 If the @code{WITH} keyword is omitted, then tests for all
1927 combinations of the listed variables are performed.
1928 If the @code{WITH} keyword is given, and the @code{(PAIRED)} keyword
1929 is also given, then the number of variables preceding @code{WITH}
1930 must be the same as the number following it.
1931 In this case, tests for each respective pair of variables are
1933 If the @code{WITH} keyword is given, but the
1934 @code{(PAIRED)} keyword is omitted, then tests for each combination
1935 of variable preceding @code{WITH} against variable following
1936 @code{WITH} are performed.
1939 @subsection Wilcoxon Matched Pairs Signed Ranks Test
1941 @cindex wilcoxon matched pairs signed ranks test
1944 [ /WILCOXON @var{var_list} [ WITH @var{var_list} [ (PAIRED) ]]]
1947 The @subcmd{/WILCOXON} subcommand tests for differences between medians of the
1949 The test does not make any assumptions about the variances of the samples.
1950 It does however assume that the distribution is symmetrical.
1952 If the @subcmd{WITH} keyword is omitted, then tests for all
1953 combinations of the listed variables are performed.
1954 If the @subcmd{WITH} keyword is given, and the @subcmd{(PAIRED)} keyword
1955 is also given, then the number of variables preceding @subcmd{WITH}
1956 must be the same as the number following it.
1957 In this case, tests for each respective pair of variables are
1959 If the @subcmd{WITH} keyword is given, but the
1960 @subcmd{(PAIRED)} keyword is omitted, then tests for each combination
1961 of variable preceding @subcmd{WITH} against variable following
1962 @subcmd{WITH} are performed.
1971 /MISSING=@{ANALYSIS,LISTWISE@} @{EXCLUDE,INCLUDE@}
1972 /CRITERIA=CI(@var{confidence})
1976 TESTVAL=@var{test_value}
1977 /VARIABLES=@var{var_list}
1980 (Independent Samples mode.)
1981 GROUPS=var(@var{value1} [, @var{value2}])
1982 /VARIABLES=@var{var_list}
1985 (Paired Samples mode.)
1986 PAIRS=@var{var_list} [WITH @var{var_list} [(PAIRED)] ]
1991 The @cmd{T-TEST} procedure outputs tables used in testing hypotheses about
1993 It operates in one of three modes:
1995 @item One Sample mode.
1996 @item Independent Groups mode.
2001 Each of these modes are described in more detail below.
2002 There are two optional subcommands which are common to all modes.
2004 The @cmd{/CRITERIA} subcommand tells @pspp{} the confidence interval used
2005 in the tests. The default value is 0.95.
2008 The @cmd{MISSING} subcommand determines the handling of missing
2010 If @subcmd{INCLUDE} is set, then user-missing values are included in the
2011 calculations, but system-missing values are not.
2012 If @subcmd{EXCLUDE} is set, which is the default, user-missing
2013 values are excluded as well as system-missing values.
2014 This is the default.
2016 If @subcmd{LISTWISE} is set, then the entire case is excluded from analysis
2017 whenever any variable specified in the @subcmd{/VARIABLES}, @subcmd{/PAIRS} or
2018 @subcmd{/GROUPS} subcommands contains a missing value.
2019 If @subcmd{ANALYSIS} is set, then missing values are excluded only in the analysis for
2020 which they would be needed. This is the default.
2024 * One Sample Mode:: Testing against a hypothesized mean
2025 * Independent Samples Mode:: Testing two independent groups for equal mean
2026 * Paired Samples Mode:: Testing two interdependent groups for equal mean
2029 @node One Sample Mode
2030 @subsection One Sample Mode
2032 The @subcmd{TESTVAL} subcommand invokes the One Sample mode.
2033 This mode is used to test a population mean against a hypothesized
2035 The value given to the @subcmd{TESTVAL} subcommand is the value against
2036 which you wish to test.
2037 In this mode, you must also use the @subcmd{/VARIABLES} subcommand to
2038 tell @pspp{} which variables you wish to test.
2040 @subsubsection Example - One Sample T-test
2042 A researcher wishes to know whether the weight of persons in a population
2043 is different from the national average.
2044 The samples are drawn from the population under investigation and recorded
2045 in the file @file{physiology.sav}.
2046 From the Department of Health, she
2047 knows that the national average weight of healthy adults is 76.8kg.
2048 Accordingly the @subcmd{TESTVAL} is set to 76.8.
2049 The null hypothesis therefore is that the mean average weight of the
2050 population from which the sample was drawn is 76.8kg.
2052 As previously noted (@pxref{Identifying incorrect data}), one
2053 sample in the dataset contains a weight value
2054 which is clearly incorrect. So this is excluded from the analysis
2055 using the @cmd{SELECT} command.
2057 @float Example, one-sample-t:ex
2058 @psppsyntax {one-sample-t.sps}
2059 @caption {Running a one sample T-Test after excluding all non-positive values}
2062 @float Screenshot, one-sample-t:scr
2063 @psppimage {one-sample-t}
2064 @caption {Using the One Sample T-Test dialog box to test @exvar{weight} for a mean of 76.8kg}
2068 @ref{one-sample-t:res} shows that the mean of our sample differs from the test value
2069 by -1.40kg. However the significance is very high (0.610). So one cannot
2070 reject the null hypothesis, and must conclude there is not enough evidence
2071 to suggest that the mean weight of the persons in our population is different
2074 @float Results, one-sample-t:res
2075 @psppoutput {one-sample-t}
2076 @caption {The results of a one sample T-test of @exvar{weight} using a test value of 76.8kg}
2079 @node Independent Samples Mode
2080 @subsection Independent Samples Mode
2082 The @subcmd{GROUPS} subcommand invokes Independent Samples mode or
2084 This mode is used to test whether two groups of values have the
2085 same population mean.
2086 In this mode, you must also use the @subcmd{/VARIABLES} subcommand to
2087 tell @pspp{} the dependent variables you wish to test.
2089 The variable given in the @subcmd{GROUPS} subcommand is the independent
2090 variable which determines to which group the samples belong.
2091 The values in parentheses are the specific values of the independent
2092 variable for each group.
2093 If the parentheses are omitted and no values are given, the default values
2094 of 1.0 and 2.0 are assumed.
2096 If the independent variable is numeric,
2097 it is acceptable to specify only one value inside the parentheses.
2098 If you do this, cases where the independent variable is
2099 greater than or equal to this value belong to the first group, and cases
2100 less than this value belong to the second group.
2101 When using this form of the @subcmd{GROUPS} subcommand, missing values in
2102 the independent variable are excluded on a listwise basis, regardless
2103 of whether @subcmd{/MISSING=LISTWISE} was specified.
2105 @subsubsection Example - Independent Samples T-test
2107 A researcher wishes to know whether within a population, adult males
2108 are taller than adult females.
2109 The samples are drawn from the population under investigation and recorded
2110 in the file @file{physiology.sav}.
2112 As previously noted (@pxref{Identifying incorrect data}), one
2113 sample in the dataset contains a height value
2114 which is clearly incorrect. So this is excluded from the analysis
2115 using the @cmd{SELECT} command.
2118 @float Example, indepdendent-samples-t:ex
2119 @psppsyntax {independent-samples-t.sps}
2120 @caption {Running a independent samples T-Test after excluding all observations less than 200kg}
2124 The null hypothesis is that both males and females are on average
2127 @float Screenshot, independent-samples-t:scr
2128 @psppimage {independent-samples-t}
2129 @caption {Using the Independent Sample T-test dialog, to test for differences of @exvar{height} between values of @exvar{sex}}
2133 In this case, the grouping variable is @exvar{sex}, so this is entered
2134 as the variable for the @subcmd{GROUP} subcommand. The group values are 0 (male) and
2137 If you are running the proceedure using syntax, then you need to enter
2138 the values corresponding to each group within parentheses.
2139 If you are using the graphic user interface, then you have to open
2140 the ``Define Groups'' dialog box and enter the values corresponding
2141 to each group as shown in @ref{define-groups-t:scr}. If, as in this case, the dataset has defined value
2142 labels for the group variable, then you can enter them by label
2145 @float Screenshot, define-groups-t:scr
2146 @psppimage {define-groups-t}
2147 @caption {Setting the values of the grouping variable for an Independent Samples T-test}
2150 From @ref{independent-samples-t:res}, one can clearly see that the @emph{sample} mean height
2151 is greater for males than for females. However in order to see if this
2152 is a significant result, one must consult the T-Test table.
2154 The T-Test table contains two rows; one for use if the variance of the samples
2155 in each group may be safely assumed to be equal, and the second row
2156 if the variances in each group may not be safely assumed to be equal.
2158 In this case however, both rows show a 2-tailed significance less than 0.001 and
2159 one must therefore reject the null hypothesis and conclude that within
2160 the population the mean height of males and of females are unequal.
2162 @float Result, independent-samples-t:res
2163 @psppoutput {independent-samples-t}
2164 @caption {The results of an independent samples T-test of @exvar{height} by @exvar{sex}}
2167 @node Paired Samples Mode
2168 @subsection Paired Samples Mode
2170 The @cmd{PAIRS} subcommand introduces Paired Samples mode.
2171 Use this mode when repeated measures have been taken from the same
2173 If the @subcmd{WITH} keyword is omitted, then tables for all
2174 combinations of variables given in the @cmd{PAIRS} subcommand are
2176 If the @subcmd{WITH} keyword is given, and the @subcmd{(PAIRED)} keyword
2177 is also given, then the number of variables preceding @subcmd{WITH}
2178 must be the same as the number following it.
2179 In this case, tables for each respective pair of variables are
2181 In the event that the @subcmd{WITH} keyword is given, but the
2182 @subcmd{(PAIRED)} keyword is omitted, then tables for each combination
2183 of variable preceding @subcmd{WITH} against variable following
2184 @subcmd{WITH} are generated.
2191 @cindex analysis of variance
2196 [/VARIABLES = ] @var{var_list} BY @var{var}
2197 /MISSING=@{ANALYSIS,LISTWISE@} @{EXCLUDE,INCLUDE@}
2198 /CONTRAST= @var{value1} [, @var{value2}] ... [,@var{valueN}]
2199 /STATISTICS=@{DESCRIPTIVES,HOMOGENEITY@}
2200 /POSTHOC=@{BONFERRONI, GH, LSD, SCHEFFE, SIDAK, TUKEY, ALPHA ([@var{value}])@}
2203 The @cmd{ONEWAY} procedure performs a one-way analysis of variance of
2204 variables factored by a single independent variable.
2205 It is used to compare the means of a population
2206 divided into more than two groups.
2208 The dependent variables to be analysed should be given in the @subcmd{VARIABLES}
2210 The list of variables must be followed by the @subcmd{BY} keyword and
2211 the name of the independent (or factor) variable.
2213 You can use the @subcmd{STATISTICS} subcommand to tell @pspp{} to display
2214 ancillary information. The options accepted are:
2217 Displays descriptive statistics about the groups factored by the independent
2220 Displays the Levene test of Homogeneity of Variance for the
2221 variables and their groups.
2224 The @subcmd{CONTRAST} subcommand is used when you anticipate certain
2225 differences between the groups.
2226 The subcommand must be followed by a list of numerals which are the
2227 coefficients of the groups to be tested.
2228 The number of coefficients must correspond to the number of distinct
2229 groups (or values of the independent variable).
2230 If the total sum of the coefficients are not zero, then @pspp{} will
2231 display a warning, but will proceed with the analysis.
2232 The @subcmd{CONTRAST} subcommand may be given up to 10 times in order
2233 to specify different contrast tests.
2234 The @subcmd{MISSING} subcommand defines how missing values are handled.
2235 If @subcmd{LISTWISE} is specified then cases which have missing values for
2236 the independent variable or any dependent variable are ignored.
2237 If @subcmd{ANALYSIS} is specified, then cases are ignored if the independent
2238 variable is missing or if the dependent variable currently being
2239 analysed is missing. The default is @subcmd{ANALYSIS}.
2240 A setting of @subcmd{EXCLUDE} means that variables whose values are
2241 user-missing are to be excluded from the analysis. A setting of
2242 @subcmd{INCLUDE} means they are to be included. The default is @subcmd{EXCLUDE}.
2244 Using the @code{POSTHOC} subcommand you can perform multiple
2245 pairwise comparisons on the data. The following comparison methods
2249 Least Significant Difference.
2250 @item @subcmd{TUKEY}
2251 Tukey Honestly Significant Difference.
2252 @item @subcmd{BONFERRONI}
2254 @item @subcmd{SCHEFFE}
2256 @item @subcmd{SIDAK}
2259 The Games-Howell test.
2263 Use the optional syntax @code{ALPHA(@var{value})} to indicate that
2264 @cmd{ONEWAY} should perform the posthoc tests at a confidence level of
2265 @var{value}. If @code{ALPHA(@var{value})} is not specified, then the
2266 confidence level used is 0.05.
2269 @section QUICK CLUSTER
2270 @vindex QUICK CLUSTER
2272 @cindex K-means clustering
2276 QUICK CLUSTER @var{var_list}
2277 [/CRITERIA=CLUSTERS(@var{k}) [MXITER(@var{max_iter})] CONVERGE(@var{epsilon}) [NOINITIAL]]
2278 [/MISSING=@{EXCLUDE,INCLUDE@} @{LISTWISE, PAIRWISE@}]
2279 [/PRINT=@{INITIAL@} @{CLUSTER@}]
2280 [/SAVE[=[CLUSTER[(@var{membership_var})]] [DISTANCE[(@var{distance_var})]]]
2283 The @cmd{QUICK CLUSTER} command performs k-means clustering on the
2284 dataset. This is useful when you wish to allocate cases into clusters
2285 of similar values and you already know the number of clusters.
2287 The minimum specification is @samp{QUICK CLUSTER} followed by the names
2288 of the variables which contain the cluster data. Normally you will also
2289 want to specify @subcmd{/CRITERIA=CLUSTERS(@var{k})} where @var{k} is the
2290 number of clusters. If this is not specified, then @var{k} defaults to 2.
2292 If you use @subcmd{/CRITERIA=NOINITIAL} then a naive algorithm to select
2293 the initial clusters is used. This will provide for faster execution but
2294 less well separated initial clusters and hence possibly an inferior final
2298 @cmd{QUICK CLUSTER} uses an iterative algorithm to select the clusters centers.
2299 The subcommand @subcmd{/CRITERIA=MXITER(@var{max_iter})} sets the maximum number of iterations.
2300 During classification, @pspp{} will continue iterating until until @var{max_iter}
2301 iterations have been done or the convergence criterion (see below) is fulfilled.
2302 The default value of @var{max_iter} is 2.
2304 If however, you specify @subcmd{/CRITERIA=NOUPDATE} then after selecting the initial centers,
2305 no further update to the cluster centers is done. In this case, @var{max_iter}, if specified.
2308 The subcommand @subcmd{/CRITERIA=CONVERGE(@var{epsilon})} is used
2309 to set the convergence criterion. The value of convergence criterion is @var{epsilon}
2310 times the minimum distance between the @emph{initial} cluster centers. Iteration stops when
2311 the mean cluster distance between one iteration and the next
2312 is less than the convergence criterion. The default value of @var{epsilon} is zero.
2314 The @subcmd{MISSING} subcommand determines the handling of missing variables.
2315 If @subcmd{INCLUDE} is set, then user-missing values are considered at their face
2316 value and not as missing values.
2317 If @subcmd{EXCLUDE} is set, which is the default, user-missing
2318 values are excluded as well as system-missing values.
2320 If @subcmd{LISTWISE} is set, then the entire case is excluded from the analysis
2321 whenever any of the clustering variables contains a missing value.
2322 If @subcmd{PAIRWISE} is set, then a case is considered missing only if all the
2323 clustering variables contain missing values. Otherwise it is clustered
2324 on the basis of the non-missing values.
2325 The default is @subcmd{LISTWISE}.
2327 The @subcmd{PRINT} subcommand requests additional output to be printed.
2328 If @subcmd{INITIAL} is set, then the initial cluster memberships will
2330 If @subcmd{CLUSTER} is set, the cluster memberships of the individual
2331 cases are displayed (potentially generating lengthy output).
2333 You can specify the subcommand @subcmd{SAVE} to ask that each case's cluster membership
2334 and the euclidean distance between the case and its cluster center be saved to
2335 a new variable in the active dataset. To save the cluster membership use the
2336 @subcmd{CLUSTER} keyword and to save the distance use the @subcmd{DISTANCE} keyword.
2337 Each keyword may optionally be followed by a variable name in parentheses to specify
2338 the new variable which is to contain the saved parameter. If no variable name is specified,
2339 then PSPP will create one.
2347 [VARIABLES=] @var{var_list} [@{A,D@}] [BY @var{var_list}]
2348 /TIES=@{MEAN,LOW,HIGH,CONDENSE@}
2349 /FRACTION=@{BLOM,TUKEY,VW,RANKIT@}
2351 /MISSING=@{EXCLUDE,INCLUDE@}
2353 /RANK [INTO @var{var_list}]
2354 /NTILES(k) [INTO @var{var_list}]
2355 /NORMAL [INTO @var{var_list}]
2356 /PERCENT [INTO @var{var_list}]
2357 /RFRACTION [INTO @var{var_list}]
2358 /PROPORTION [INTO @var{var_list}]
2359 /N [INTO @var{var_list}]
2360 /SAVAGE [INTO @var{var_list}]
2363 The @cmd{RANK} command ranks variables and stores the results into new
2366 The @subcmd{VARIABLES} subcommand, which is mandatory, specifies one or
2367 more variables whose values are to be ranked.
2368 After each variable, @samp{A} or @samp{D} may appear, indicating that
2369 the variable is to be ranked in ascending or descending order.
2370 Ascending is the default.
2371 If a @subcmd{BY} keyword appears, it should be followed by a list of variables
2372 which are to serve as group variables.
2373 In this case, the cases are gathered into groups, and ranks calculated
2376 The @subcmd{TIES} subcommand specifies how tied values are to be treated. The
2377 default is to take the mean value of all the tied cases.
2379 The @subcmd{FRACTION} subcommand specifies how proportional ranks are to be
2380 calculated. This only has any effect if @subcmd{NORMAL} or @subcmd{PROPORTIONAL} rank
2381 functions are requested.
2383 The @subcmd{PRINT} subcommand may be used to specify that a summary of the rank
2384 variables created should appear in the output.
2386 The function subcommands are @subcmd{RANK}, @subcmd{NTILES}, @subcmd{NORMAL}, @subcmd{PERCENT}, @subcmd{RFRACTION},
2387 @subcmd{PROPORTION} and @subcmd{SAVAGE}. Any number of function subcommands may appear.
2388 If none are given, then the default is RANK.
2389 The @subcmd{NTILES} subcommand must take an integer specifying the number of
2390 partitions into which values should be ranked.
2391 Each subcommand may be followed by the @subcmd{INTO} keyword and a list of
2392 variables which are the variables to be created and receive the rank
2393 scores. There may be as many variables specified as there are
2394 variables named on the @subcmd{VARIABLES} subcommand. If fewer are specified,
2395 then the variable names are automatically created.
2397 The @subcmd{MISSING} subcommand determines how user missing values are to be
2398 treated. A setting of @subcmd{EXCLUDE} means that variables whose values are
2399 user-missing are to be excluded from the rank scores. A setting of
2400 @subcmd{INCLUDE} means they are to be included. The default is @subcmd{EXCLUDE}.
2402 @include regression.texi
2406 @section RELIABILITY
2411 /VARIABLES=@var{var_list}
2412 /SCALE (@var{name}) = @{@var{var_list}, ALL@}
2413 /MODEL=@{ALPHA, SPLIT[(@var{n})]@}
2414 /SUMMARY=@{TOTAL,ALL@}
2415 /MISSING=@{EXCLUDE,INCLUDE@}
2418 @cindex Cronbach's Alpha
2419 The @cmd{RELIABILITY} command performs reliability analysis on the data.
2421 The @subcmd{VARIABLES} subcommand is required. It determines the set of variables
2422 upon which analysis is to be performed.
2424 The @subcmd{SCALE} subcommand determines the variables for which
2425 reliability is to be calculated. If @subcmd{SCALE} is omitted, then analysis for
2426 all variables named in the @subcmd{VARIABLES} subcommand are used.
2427 Optionally, the @var{name} parameter may be specified to set a string name
2430 The @subcmd{MODEL} subcommand determines the type of analysis. If @subcmd{ALPHA} is specified,
2431 then Cronbach's Alpha is calculated for the scale. If the model is @subcmd{SPLIT},
2432 then the variables are divided into 2 subsets. An optional parameter
2433 @var{n} may be given, to specify how many variables to be in the first subset.
2434 If @var{n} is omitted, then it defaults to one half of the variables in the
2435 scale, or one half minus one if there are an odd number of variables.
2436 The default model is @subcmd{ALPHA}.
2438 By default, any cases with user missing, or system missing values for
2439 any variables given in the @subcmd{VARIABLES} subcommand are omitted
2440 from the analysis. The @subcmd{MISSING} subcommand determines whether
2441 user missing values are included or excluded in the analysis.
2443 The @subcmd{SUMMARY} subcommand determines the type of summary analysis to be performed.
2444 Currently there is only one type: @subcmd{SUMMARY=TOTAL}, which displays per-item
2445 analysis tested against the totals.
2447 @subsection Example - Reliability
2449 Before analysing the results of a survey -- particularly for a multiple choice survey --
2450 it is desireable to know whether the respondents have considered their answers
2451 or simply provided random answers.
2453 In the following example the survey results from the file @file{hotel.sav} are used.
2454 All five survey questions are included in the reliability analysis.
2455 However, before running the analysis, the data must be preprocessed.
2456 An examination of the survey questions reveals that two questions, @i{viz:} v3 and v5
2457 are negatively worded, whereas the others are positively worded.
2458 All questions must be based upon the same scale for the analysis to be meaningful.
2459 One could use the @cmd{RECODE} command (@pxref{RECODE}), however a simpler way is
2460 to use @cmd{COMPUTE} (@pxref{COMPUTE}) and this is what is done in @ref{reliability:ex}.
2462 @float Example, reliability:ex
2463 @psppsyntax {reliability.sps}
2464 @caption {Investigating the reliability of survey responses}
2467 In this case, all variables in the data set are used. So we can use the special
2468 keyword @samp{ALL} (@pxref{BNF}).
2470 @float Screenshot, reliability:src
2471 @psppimage {reliability}
2472 @caption {Reliability dialog box with all variables selected}
2475 @ref{reliability:res} shows that Cronbach's Alpha is 0.11 which is a value normally considered too
2476 low to indicate consistency within the data. This is possibly due to the small number of
2477 survey questions. The survey should be redesigned before serious use of the results are
2480 @float Result, reliability:res
2481 @psppoutput {reliability}
2482 @caption {The results of the reliability command on @file{hotel.sav}}
2490 @cindex Receiver Operating Characteristic
2491 @cindex Area under curve
2494 ROC @var{var_list} BY @var{state_var} (@var{state_value})
2495 /PLOT = @{ CURVE [(REFERENCE)], NONE @}
2496 /PRINT = [ SE ] [ COORDINATES ]
2497 /CRITERIA = [ CUTOFF(@{INCLUDE,EXCLUDE@}) ]
2498 [ TESTPOS (@{LARGE,SMALL@}) ]
2499 [ CI (@var{confidence}) ]
2500 [ DISTRIBUTION (@{FREE, NEGEXPO @}) ]
2501 /MISSING=@{EXCLUDE,INCLUDE@}
2505 The @cmd{ROC} command is used to plot the receiver operating characteristic curve
2506 of a dataset, and to estimate the area under the curve.
2507 This is useful for analysing the efficacy of a variable as a predictor of a state of nature.
2509 The mandatory @var{var_list} is the list of predictor variables.
2510 The variable @var{state_var} is the variable whose values represent the actual states,
2511 and @var{state_value} is the value of this variable which represents the positive state.
2513 The optional subcommand @subcmd{PLOT} is used to determine if and how the @subcmd{ROC} curve is drawn.
2514 The keyword @subcmd{CURVE} means that the @subcmd{ROC} curve should be drawn, and the optional keyword @subcmd{REFERENCE},
2515 which should be enclosed in parentheses, says that the diagonal reference line should be drawn.
2516 If the keyword @subcmd{NONE} is given, then no @subcmd{ROC} curve is drawn.
2517 By default, the curve is drawn with no reference line.
2519 The optional subcommand @subcmd{PRINT} determines which additional
2520 tables should be printed. Two additional tables are available. The
2521 @subcmd{SE} keyword says that standard error of the area under the
2522 curve should be printed as well as the area itself. In addition, a
2523 p-value for the null hypothesis that the area under the curve equals
2524 0.5 is printed. The @subcmd{COORDINATES} keyword says that a
2525 table of coordinates of the @subcmd{ROC} curve should be printed.
2527 The @subcmd{CRITERIA} subcommand has four optional parameters:
2529 @item The @subcmd{TESTPOS} parameter may be @subcmd{LARGE} or @subcmd{SMALL}.
2530 @subcmd{LARGE} is the default, and says that larger values in the predictor variables are to be
2531 considered positive. @subcmd{SMALL} indicates that smaller values should be considered positive.
2533 @item The @subcmd{CI} parameter specifies the confidence interval that should be printed.
2534 It has no effect if the @subcmd{SE} keyword in the @subcmd{PRINT} subcommand has not been given.
2536 @item The @subcmd{DISTRIBUTION} parameter determines the method to be used when estimating the area
2538 There are two possibilities, @i{viz}: @subcmd{FREE} and @subcmd{NEGEXPO}.
2539 The @subcmd{FREE} method uses a non-parametric estimate, and the @subcmd{NEGEXPO} method a bi-negative
2540 exponential distribution estimate.
2541 The @subcmd{NEGEXPO} method should only be used when the number of positive actual states is
2542 equal to the number of negative actual states.
2543 The default is @subcmd{FREE}.
2545 @item The @subcmd{CUTOFF} parameter is for compatibility and is ignored.
2548 The @subcmd{MISSING} subcommand determines whether user missing values are to
2549 be included or excluded in the analysis. The default behaviour is to
2551 Cases are excluded on a listwise basis; if any of the variables in @var{var_list}
2552 or if the variable @var{state_var} is missing, then the entire case is
2555 @c LocalWords: subcmd subcommand