4 This chapter documents the statistical procedures that PSPP supports so
8 * DESCRIPTIVES:: Descriptive statistics.
9 * FREQUENCIES:: Frequency tables.
10 * EXAMINE:: Testing data for normality.
11 * CROSSTABS:: Crosstabulation tables.
12 * NPAR TESTS:: Nonparametric tests.
13 * T-TEST:: Test hypotheses about means.
14 * ONEWAY:: One way analysis of variance.
15 * RANK:: Compute rank scores.
16 * REGRESSION:: Linear regression.
26 /MISSING=@{VARIABLE,LISTWISE@} @{INCLUDE,NOINCLUDE@}
27 /FORMAT=@{LABELS,NOLABELS@} @{NOINDEX,INDEX@} @{LINE,SERIAL@}
29 /STATISTICS=@{ALL,MEAN,SEMEAN,STDDEV,VARIANCE,KURTOSIS,
30 SKEWNESS,RANGE,MINIMUM,MAXIMUM,SUM,DEFAULT,
31 SESKEWNESS,SEKURTOSIS@}
32 /SORT=@{NONE,MEAN,SEMEAN,STDDEV,VARIANCE,KURTOSIS,SKEWNESS,
33 RANGE,MINIMUM,MAXIMUM,SUM,SESKEWNESS,SEKURTOSIS,NAME@}
37 The @cmd{DESCRIPTIVES} procedure reads the active file and outputs
39 statistics requested by the user. In addition, it can optionally
42 The VARIABLES subcommand, which is required, specifies the list of
43 variables to be analyzed. Keyword VARIABLES is optional.
45 All other subcommands are optional:
47 The MISSING subcommand determines the handling of missing variables. If
48 INCLUDE is set, then user-missing values are included in the
49 calculations. If NOINCLUDE is set, which is the default, user-missing
50 values are excluded. If VARIABLE is set, then missing values are
51 excluded on a variable by variable basis; if LISTWISE is set, then
52 the entire case is excluded whenever any value in that case has a
53 system-missing or, if INCLUDE is set, user-missing value.
55 The FORMAT subcommand affects the output format. Currently the
56 LABELS/NOLABELS and NOINDEX/INDEX settings are not used. When SERIAL is
57 set, both valid and missing number of cases are listed in the output;
58 when NOSERIAL is set, only valid cases are listed.
60 The SAVE subcommand causes @cmd{DESCRIPTIVES} to calculate Z scores for all
61 the specified variables. The Z scores are saved to new variables.
62 Variable names are generated by trying first the original variable name
63 with Z prepended and truncated to a maximum of 8 characters, then the
64 names ZSC000 through ZSC999, STDZ00 through STDZ09, ZZZZ00 through
65 ZZZZ09, ZQZQ00 through ZQZQ09, in that sequence. In addition, Z score
66 variable names can be specified explicitly on VARIABLES in the variable
67 list by enclosing them in parentheses after each variable.
69 The STATISTICS subcommand specifies the statistics to be displayed:
73 All of the statistics below.
77 Standard error of the mean.
83 Kurtosis and standard error of the kurtosis.
85 Skewness and standard error of the skewness.
95 Mean, standard deviation of the mean, minimum, maximum.
97 Standard error of the kurtosis.
99 Standard error of the skewness.
102 The SORT subcommand specifies how the statistics should be sorted. Most
103 of the possible values should be self-explanatory. NAME causes the
104 statistics to be sorted by name. By default, the statistics are listed
105 in the order that they are specified on the VARIABLES subcommand. The A
106 and D settings request an ascending or descending sort order,
116 /FORMAT=@{TABLE,NOTABLE,LIMIT(limit)@}
117 @{STANDARD,CONDENSE,ONEPAGE[(onepage_limit)]@}
119 @{AVALUE,DVALUE,AFREQ,DFREQ@}
122 /MISSING=@{EXCLUDE,INCLUDE@}
123 /STATISTICS=@{DEFAULT,MEAN,SEMEAN,MEDIAN,MODE,STDDEV,VARIANCE,
124 KURTOSIS,SKEWNESS,RANGE,MINIMUM,MAXIMUM,SUM,
125 SESKEWNESS,SEKURTOSIS,ALL,NONE@}
127 /PERCENTILES=percent@dots{}
128 /HISTOGRAM=[MINIMUM(x_min)] [MAXIMUM(x_max)]
129 [@{FREQ,PCNT@}] [@{NONORMAL,NORMAL@}]
130 /PIECHART=[MINIMUM(x_min)] [MAXIMUM(x_max)] @{NOMISSING,MISSING@}
132 (These options are not currently implemented.)
138 The @cmd{FREQUENCIES} procedure outputs frequency tables for specified
140 @cmd{FREQUENCIES} can also calculate and display descriptive statistics
141 (including median and mode) and percentiles.
143 @cmd{FREQUENCIES} also support graphical output in the form of
144 histograms and pie charts. In the future, it will be able to produce
145 bar charts and output percentiles for grouped data.
147 The VARIABLES subcommand is the only required subcommand. Specify the
148 variables to be analyzed.
150 The FORMAT subcommand controls the output format. It has several
155 TABLE, the default, causes a frequency table to be output for every
156 variable specified. NOTABLE prevents them from being output. LIMIT
157 with a numeric argument causes them to be output except when there are
158 more than the specified number of values in the table.
161 STANDARD frequency tables contain more complete information, but also to
162 take up more space on the printed page. CONDENSE frequency tables are
163 less informative but take up less space. ONEPAGE with a numeric
164 argument will output standard frequency tables if there are the
165 specified number of values or less, condensed tables otherwise. ONEPAGE
166 without an argument defaults to a threshold of 50 values.
169 LABELS causes value labels to be displayed in STANDARD frequency
170 tables. NOLABLES prevents this.
173 Normally frequency tables are sorted in ascending order by value. This
174 is AVALUE. DVALUE tables are sorted in descending order by value.
175 AFREQ and DFREQ tables are sorted in ascending and descending order,
176 respectively, by frequency count.
179 SINGLE spaced frequency tables are closely spaced. DOUBLE spaced
180 frequency tables have wider spacing.
183 OLDPAGE and NEWPAGE are not currently used.
186 The MISSING subcommand controls the handling of user-missing values.
187 When EXCLUDE, the default, is set, user-missing values are not included
188 in frequency tables or statistics. When INCLUDE is set, user-missing
189 are included. System-missing values are never included in statistics,
190 but are listed in frequency tables.
192 The available STATISTICS are the same as available in @cmd{DESCRIPTIVES}
193 (@pxref{DESCRIPTIVES}), with the addition of MEDIAN, the data's median
194 value, and MODE, the mode. (If there are multiple modes, the smallest
195 value is reported.) By default, the mean, standard deviation of the
196 mean, minimum, and maximum are reported for each variable.
199 PERCENTILES causes the specified percentiles to be reported.
200 The percentiles should be presented at a list of numbers between 0
202 The NTILES subcommand causes the percentiles to be reported at the
203 boundaries of the data set divided into the specified number of ranges.
204 For instance, @code{/NTILES=4} would cause quartiles to be reported.
206 The HISTOGRAM subcommand causes the output to include a histogram for
207 each specified variable. The X axis by default ranges from the
208 minimum to the maximum value observed in the data, but the MINIMUM and
209 MAXIMUM keywords can set an explicit range. The Y axis by default is
210 labeled in frequencies; use the PERCENT keyword to causes it to be
211 labeled in percent of the total observed count. Specify NORMAL to
212 superimpose a normal curve on the histogram.
214 The PIECHART adds a pie chart for each variable to the data. Each
215 slice represents one value, with the size of the slice proportional to
216 the value's frequency. By default, all non-missing values are given
217 slices. The MINIMUM and MAXIMUM keywords can be used to limit the
218 displayed slices to a given range of values. The MISSING keyword adds
219 slices for missing values.
222 @comment node-name, next, previous, up
226 @cindex Normality, testing for
230 VARIABLES=var_list [BY factor_list ]
231 /STATISTICS=@{DESCRIPTIVES, EXTREME[(n)], ALL, NONE@}
232 /PLOT=@{BOXPLOT, NPPLOT, HISTOGRAM, ALL, NONE@}
234 /COMPARE=@{GROUPS,VARIABLES@}
235 /ID=@{case_number, var_name@}
237 /PERCENTILE=[value_list]=@{HAVERAGE, WAVERAGE, ROUND, AEMPIRICAL, EMPIRICAL @}
238 /MISSING=@{LISTWISE, PAIRWISE@} [@{EXCLUDE, INCLUDE@}]
239 [@{NOREPORT,REPORT@}]
243 The @cmd{EXAMINE} command is used to test how closely a distribution is to a
244 normal distribution. It also shows you outliers and extreme values.
246 The VARIABLES subcommand specifies the dependent variables and the
247 independent variable to use as factors for the analysis. Variables
248 listed before the first BY keyword are the dependent variables.
249 The dependent variables may optionally be followed by a list of
250 factors which tell PSPP how to break down the analysis for each
251 dependent variable. The format for each factor is
257 The STATISTICS subcommand specifies the analysis to be done.
258 DESCRIPTIVES will produce a table showing some parametric and
259 non-parametrics statistics. EXTREME produces a table showing extreme
260 values of the dependent variable. A number in parentheses determines
261 how many upper and lower extremes to show. The default number is 5.
264 The PLOT subcommand specifies which plots are to be produced if any.
266 The COMPARE subcommand is only relevant if producing boxplots, and it is only
267 useful there is more than one dependent variable and at least one factor. If
268 /COMPARE=GROUPS is specified, then one plot per dependent variable is produced,
269 containing boxplots for all the factors.
270 If /COMPARE=VARIABLES is specified, then one plot per factor is produced, each
271 each containing one boxplot per dependent variable.
272 If the /COMPARE subcommand is ommitted, then PSPP uses the default value of
275 The CINTERVAL subcommand specifies the confidence interval to use in
276 calculation of the descriptives command. The default it 95%.
279 The PERCENTILES subcommand specifies which percentiles are to be calculated,
280 and which algorithm to use for calculating them. The default is to
281 calculate the 5, 10, 25, 50, 75, 90, 95 percentiles using the
284 The TOTAL and NOTOTAL subcommands are mutually exclusive. If NOTOTAL
285 is given and factors have been specified in the VARIABLES subcommand,
286 then then statistics for the unfactored dependent variables are
287 produced in addition to the factored variables. If there are no
288 factors specified then TOTAL and NOTOTAL have no effect.
291 If many dependent variable are given, or factors are given for which
292 there are many distinct values, then @cmd{EXAMINE} will produce a very
293 large quantity of output.
302 /TABLES=var_list BY var_list [BY var_list]@dots{}
303 /MISSING=@{TABLE,INCLUDE,REPORT@}
304 /WRITE=@{NONE,CELLS,ALL@}
305 /FORMAT=@{TABLES,NOTABLES@}
306 @{LABELS,NOLABELS,NOVALLABS@}
311 /CELLS=@{COUNT,ROW,COLUMN,TOTAL,EXPECTED,RESIDUAL,SRESIDUAL,
312 ASRESIDUAL,ALL,NONE@}
313 /STATISTICS=@{CHISQ,PHI,CC,LAMBDA,UC,BTAU,CTAU,RISK,GAMMA,D,
314 KAPPA,ETA,CORR,ALL,NONE@}
317 /VARIABLES=var_list (low,high)@dots{}
320 The @cmd{CROSSTABS} procedure displays crosstabulation
321 tables requested by the user. It can calculate several statistics for
322 each cell in the crosstabulation tables. In addition, a number of
323 statistics can be calculated for each table itself.
325 The TABLES subcommand is used to specify the tables to be reported. Any
326 number of dimensions is permitted, and any number of variables per
327 dimension is allowed. The TABLES subcommand may be repeated as many
328 times as needed. This is the only required subcommand in @dfn{general
331 Occasionally, one may want to invoke a special mode called @dfn{integer
332 mode}. Normally, in general mode, PSPP automatically determines
333 what values occur in the data. In integer mode, the user specifies the
334 range of values that the data assumes. To invoke this mode, specify the
335 VARIABLES subcommand, giving a range of data values in parentheses for
336 each variable to be used on the TABLES subcommand. Data values inside
337 the range are truncated to the nearest integer, then assigned to that
338 value. If values occur outside this range, they are discarded. When it
339 is present, the VARIABLES subcommand must precede the TABLES
342 In general mode, numeric and string variables may be specified on
343 TABLES. Although long string variables are allowed, only their
344 initial short-string parts are used. In integer mode, only numeric
345 variables are allowed.
347 The MISSING subcommand determines the handling of user-missing values.
348 When set to TABLE, the default, missing values are dropped on a table by
349 table basis. When set to INCLUDE, user-missing values are included in
350 tables and statistics. When set to REPORT, which is allowed only in
351 integer mode, user-missing values are included in tables but marked with
352 an @samp{M} (for ``missing'') and excluded from statistical
355 Currently the WRITE subcommand is ignored.
357 The FORMAT subcommand controls the characteristics of the
358 crosstabulation tables to be displayed. It has a number of possible
363 TABLES, the default, causes crosstabulation tables to be output.
364 NOTABLES suppresses them.
367 LABELS, the default, allows variable labels and value labels to appear
368 in the output. NOLABELS suppresses them. NOVALLABS displays variable
369 labels but suppresses value labels.
372 PIVOT, the default, causes each TABLES subcommand to be displayed in a
373 pivot table format. NOPIVOT causes the old-style crosstabulation format
377 AVALUE, the default, causes values to be sorted in ascending order.
378 DVALUE asserts a descending sort order.
381 INDEX/NOINDEX is currently ignored.
384 BOX/NOBOX is currently ignored.
387 The CELLS subcommand controls the contents of each cell in the displayed
388 crosstabulation table. The possible settings are:
404 Standardized residual.
406 Adjusted standardized residual.
410 Suppress cells entirely.
413 @samp{/CELLS} without any settings specified requests COUNT, ROW,
414 COLUMN, and TOTAL. If CELLS is not specified at all then only COUNT
417 The STATISTICS subcommand selects statistics for computation:
424 Pearson chi-square, likelihood ratio, Fisher's exact test, continuity
425 correction, linear-by-linear association.
429 Contingency coefficient.
433 Uncertainty coefficient.
449 Spearman correlation, Pearson's r.
456 Selected statistics are only calculated when appropriate for the
457 statistic. Certain statistics require tables of a particular size, and
458 some statistics are calculated only in integer mode.
460 @samp{/STATISTICS} without any settings selects CHISQ. If the
461 STATISTICS subcommand is not given, no statistics are calculated.
463 @strong{Please note:} Currently the implementation of CROSSTABS has the
468 Pearson's R (but not Spearman) is off a little.
470 T values for Spearman's R and Pearson's R are wrong.
472 Significance of symmetric and directional measures is not calculated.
474 Asymmetric ASEs and T values for lambda are wrong.
476 ASE of Goodman and Kruskal's tau is not calculated.
478 ASE of symmetric somers' d is wrong.
480 Approximate T of uncertainty coefficient is wrong.
483 Fixes for any of these deficiencies would be welcomed.
489 @cindex nonparametric tests
494 nonparametric test subcommands
499 [ /STATISTICS=@{DESCRIPTIVES@} ]
501 [ /MISSING=@{ANALYSIS, LISTWISE@} @{INCLUDE, EXCLUDE@} ]
504 NPAR TESTS performs nonparametric tests.
505 Non parametric tests make very few assumptions about the distribution of the
507 One or more tests may be specified by using the corresponding subcommand.
508 If the /STATISTICS subcommand is also specified, then summary statistics are
509 produces for each variable that is the subject of any test.
513 * BINOMIAL:: Binomial Test
514 * CHISQUARE:: Chisquare Test
519 @subsection Binomial test
521 @cindex binomial test
524 [ /BINOMIAL[(p)]=var_list[(value1[, value2)] ] ]
527 The binomial test compares the observed distribution of a dichotomous
528 variable with that of a binomial distribution.
529 The variable @var{p} specifies the test proportion of the binomial
531 The default value of 0.5 is assumed if @var{p} is omitted.
533 If a single value appears after the variable list, then that value is
534 used as the threshold to partition the observed values. Values less
535 than or equal to the threshold value form the first category. Values
536 greater than the threshold form the second category.
538 If two values appear after the variable list, then they will be used
539 as the values which a variable must take to be in the respective
541 Cases for which a variable takes a value equal to neither of the specified
542 values, take no part in the test for that variable.
544 If no values appear, then the variable must assume dichotomous
546 If more than two distinct, non-missing values for a variable
547 under test are encountered then an error occurs.
549 If the test proportion is equal to 0.5, then a one tailed test is
550 reported. For any other test proportion, a one tailed test is
552 For one tailed tests, if the test proportion is less than
553 or equal to the observed proportion, then the significance of
554 observing the observed proportion or more is reported.
555 If the test proportion is more than the observed proportion, then the
556 significance of observing the observed proportion or less is reported.
557 That is to say, the test is always performed in the observed
560 PSPP uses a very precise approximation to the gamma function to
561 compute the binomial significance. Thus, exact results are reported
562 even for very large sample sizes.
567 @subsection Chisquare test
569 @cindex chisquare test
573 [ /CHISQUARE=var_list[(lo,hi)] [/EXPECTED=@{EQUAL|f1, f2 @dots{} fn@}] ]
577 The chisquare test produces a chi-square statistic for the differences
578 between the expected and observed frequencies of the categories of a variable.
579 Optionally, a range of values may appear after the variable list.
580 If a range is given, then non integer values are truncated, and values
581 outside the specified range are excluded from the analysis.
583 The /EXPECTED subcommand specifies the expected values of each
585 There must be exactly one non-zero expected value, for each observed
586 category, or the EQUAL keywork must be specified.
587 You may use the notation @var{n}*@var{f} to specify @var{n}
588 consecutive expected categories all taking a frequency of @var{f}.
589 The frequencies given are proportions, not absolute frequencies. The
590 sum of the frequencies need not be 1.
591 If no /EXPECTED subcommand is given, then then equal frequencies
596 @comment node-name, next, previous, up
603 /MISSING=@{ANALYSIS,LISTWISE@} @{EXCLUDE,INCLUDE@}
604 /CRITERIA=CIN(confidence)
612 (Independent Samples mode.)
613 GROUPS=var(value1 [, value2])
617 (Paired Samples mode.)
618 PAIRS=var_list [WITH var_list [(PAIRED)] ]
623 The @cmd{T-TEST} procedure outputs tables used in testing hypotheses about
625 It operates in one of three modes:
627 @item One Sample mode.
628 @item Independent Groups mode.
633 Each of these modes are described in more detail below.
634 There are two optional subcommands which are common to all modes.
636 The @cmd{/CRITERIA} subcommand tells PSPP the confidence interval used
637 in the tests. The default value is 0.95.
640 The @cmd{MISSING} subcommand determines the handling of missing
642 If INCLUDE is set, then user-missing values are included in the
643 calculations, but system-missing values are not.
644 If EXCLUDE is set, which is the default, user-missing
645 values are excluded as well as system-missing values.
648 If LISTWISE is set, then the entire case is excluded from analysis
649 whenever any variable specified in the @cmd{/VARIABLES}, @cmd{/PAIRS} or
650 @cmd{/GROUPS} subcommands contains a missing value.
651 If ANALYSIS is set, then missing values are excluded only in the analysis for
652 which they would be needed. This is the default.
656 * One Sample Mode:: Testing against a hypothesised mean
657 * Independent Samples Mode:: Testing two independent groups for equal mean
658 * Paired Samples Mode:: Testing two interdependent groups for equal mean
661 @node One Sample Mode
662 @subsection One Sample Mode
664 The @cmd{TESTVAL} subcommand invokes the One Sample mode.
665 This mode is used to test a population mean against a hypothesised
667 The value given to the @cmd{TESTVAL} subcommand is the value against
668 which you wish to test.
669 In this mode, you must also use the @cmd{/VARIABLES} subcommand to
670 tell PSPP which variables you wish to test.
672 @node Independent Samples Mode
673 @comment node-name, next, previous, up
674 @subsection Independent Samples Mode
676 The @cmd{GROUPS} subcommand invokes Independent Samples mode or
678 This mode is used to test whether two groups of values have the
679 same population mean.
680 In this mode, you must also use the @cmd{/VARIABLES} subcommand to
681 tell PSPP the dependent variables you wish to test.
683 The variable given in the @cmd{GROUPS} subcommand is the independent
684 variable which determines to which group the samples belong.
685 The values in parentheses are the specific values of the independent
686 variable for each group.
687 If the parentheses are omitted and no values are given, the default values
688 of 1.0 and 2.0 are assumed.
690 If the independent variable is numeric,
691 it is acceptable to specify only one value inside the parentheses.
692 If you do this, cases where the independent variable is
693 greater than or equal to this value belong to the first group, and cases
694 less than this value belong to the second group.
695 When using this form of the @cmd{GROUPS} subcommand, missing values in
696 the independent variable are excluded on a listwise basis, regardless
697 of whether @cmd{/MISSING=LISTWISE} was specified.
700 @node Paired Samples Mode
701 @comment node-name, next, previous, up
702 @subsection Paired Samples Mode
704 The @cmd{PAIRS} subcommand introduces Paired Samples mode.
705 Use this mode when repeated measures have been taken from the same
707 If the @code{WITH} keyword is omitted, then tables for all
708 combinations of variables given in the @cmd{PAIRS} subcommand are
710 If the @code{WITH} keyword is given, and the @code{(PAIRED)} keyword
711 is also given, then the number of variables preceding @code{WITH}
712 must be the same as the number following it.
713 In this case, tables for each respective pair of variables are
715 In the event that the @code{WITH} keyword is given, but the
716 @code{(PAIRED)} keyword is omitted, then tables for each combination
717 of variable preceding @code{WITH} against variable following
718 @code{WITH} are generated.
722 @comment node-name, next, previous, up
726 @cindex analysis of variance
731 [/VARIABLES = ] var_list BY var
732 /MISSING=@{ANALYSIS,LISTWISE@} @{EXCLUDE,INCLUDE@}
733 /CONTRAST= value1 [, value2] ... [,valueN]
734 /STATISTICS=@{DESCRIPTIVES,HOMOGENEITY@}
738 The @cmd{ONEWAY} procedure performs a one-way analysis of variance of
739 variables factored by a single independent variable.
740 It is used to compare the means of a population
741 divided into more than two groups.
743 The variables to be analysed should be given in the @code{VARIABLES}
745 The list of variables must be followed by the @code{BY} keyword and
746 the name of the independent (or factor) variable.
748 You can use the @code{STATISTICS} subcommand to tell PSPP to display
749 ancilliary information. The options accepted are:
752 Displays descriptive statistics about the groups factored by the independent
755 Displays the Levene test of Homogeneity of Variance for the
756 variables and their groups.
759 The @code{CONTRAST} subcommand is used when you anticipate certain
760 differences between the groups.
761 The subcommand must be followed by a list of numerals which are the
762 coefficients of the groups to be tested.
763 The number of coefficients must correspond to the number of distinct
764 groups (or values of the independent variable).
765 If the total sum of the coefficients are not zero, then PSPP will
766 display a warning, but will proceed with the analysis.
767 The @code{CONTRAST} subcommand may be given up to 10 times in order
768 to specify different contrast tests.
772 @comment node-name, next, previous, up
778 [VARIABLES=] var_list [@{A,D@}] [BY var_list]
779 /TIES=@{MEAN,LOW,HIGH,CONDENSE@}
780 /FRACTION=@{BLOM,TUKEY,VW,RANKIT@}
782 /MISSING=@{EXCLUDE,INCLUDE@}
784 /RANK [INTO var_list]
785 /NTILES(k) [INTO var_list]
786 /NORMAL [INTO var_list]
787 /PERCENT [INTO var_list]
788 /RFRACTION [INTO var_list]
789 /PROPORTION [INTO var_list]
791 /SAVAGE [INTO var_list]
794 The @cmd{RANK} command ranks variables and stores the results into new
797 The VARIABLES subcommand, which is mandatory, specifies one or
798 more variables whose values are to be ranked.
799 After each variable, @samp{A} or @samp{D} may appear, indicating that
800 the variable is to be ranked in ascending or descending order.
801 Ascending is the default.
802 If a BY keyword appears, it should be followed by a list of variables
803 which are to serve as group variables.
804 In this case, the cases are gathered into groups, and ranks calculated
807 The TIES subcommand specifies how tied values are to be treated. The
808 default is to take the mean value of all the tied cases.
810 The FRACTION subcommand specifies how proportional ranks are to be
811 calculated. This only has any effect if NORMAL or PROPORTIONAL rank
812 functions are requested.
814 The PRINT subcommand may be used to specify that a summary of the rank
815 variables created should appear in the output.
817 The function subcommands are RANK, NTILES, NORMAL, PERCENT, RFRACTION,
818 PROPORTION and SAVAGE. Any number of function subcommands may appear.
819 If none are given, then the default is RANK.
820 The NTILES subcommand must take an integer specifying the number of
821 partitions into which values should be ranked.
822 Each subcommand may be followed by the INTO keyword and a list of
823 variables which are the variables to be created and receive the rank
824 scores. There may be as many variables specified as there are
825 variables named on the VARIABLES subcommand. If fewer are specified,
826 then the variable names are automatically created.
828 The MISSING subcommand determines how user missing values are to be
829 treated. A setting of EXCLUDE means that variables whose values are
830 user-missing are to be excluded from the rank scores. A setting of
831 INCLUDE means they are to be included. The default is EXCLUDE.
833 @include regression.texi