X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=doc%2Fstatistics.texi;h=6957b3836eae3a2c07f8bad2f64d30d781db1249;hb=2dd762f7a21ca4e1ac232eb5350f19fd1e70be0f;hp=2f74f883fd1e7dda67622f7a9634abcf78d8677f;hpb=f751a381d7b792ee539ff2297a2b1ab9afe2d8c3;p=pspp

diff --git a/doc/statistics.texi b/doc/statistics.texi
index 2f74f883fd..6957b3836e 100644
--- a/doc/statistics.texi
+++ b/doc/statistics.texi
@@ -20,6 +20,7 @@ far.
 * GRAPH::                       Plot data.
 * CORRELATIONS::                Correlation tables.
 * CROSSTABS::                   Crosstabulation tables.
+* CTABLES::                     Custom tables.
 * FACTOR::                      Factor analysis and Principal Components analysis.
 * GLM::                         Univariate Linear Models.
 * LOGISTIC REGRESSION::         Bivariate Logistic Regression.
@@ -29,7 +30,6 @@ far.
 * ONEWAY::                      One way analysis of variance.
 * QUICK CLUSTER::               K-Means clustering.
 * RANK::                        Compute rank scores.
-* REGRESSION::                  Linear regression.
 * RELIABILITY::                 Reliability analysis.
 * ROC::                         Receiver Operating Characteristic.
 @end menu
@@ -513,9 +513,9 @@ The @cmd{GRAPH} command produces graphical plots of data. Only one of the subcom
 can be produced per call of @cmd{GRAPH}. The @subcmd{MISSING} is optional.
 
 @menu
-* SCATTERPLOT::             Cartesian Plots
-* HISTOGRAM::               Histograms
-* BAR CHART::               Bar Charts
+* SCATTERPLOT::                 Cartesian Plots
+* HISTOGRAM::                   Histograms
+* BAR CHART::                   Bar Charts
 @end menu
 
 @node SCATTERPLOT
@@ -897,6 +897,170 @@ person's occupation.
 @caption {The results of a test of independence between @exvar{sex} and @exvar{occupation}}
 @end float
 
+@node CTABLES
+@section CTABLES
+
+@vindex CTABLES
+@cindex custom tables
+@cindex tables, custom
+
+@code{CTABLES} has the following overall syntax.  At least one
+@code{TABLE} subcommand is required:
+
+@display
+@t{CTABLES}
+  @dots{}@i{global subcommands}@dots{}
+  [@t{/TABLE} @i{axis} [@t{BY} @i{axis} [@t{BY} @i{axis}]]
+   @dots{}@i{per-table subcommands}@dots{}]@dots{}
+@end display
+
+@noindent
+where each @i{axis} may be empty or take one of the following forms:
+
+@display
+@i{variable}
+@i{variable} @t{[}@{@t{C} @math{|} @t{S}@}@t{]}
+@i{axis} + @i{axis}
+@i{axis} > @i{axis}
+(@i{axis})
+@i{axis} @t{(}@i{summary} [@i{string}] [@i{format}]@t{)}
+@end display
+
+The following subcommands precede the first @code{TABLE} subcommand
+and apply to all of the output tables.  All of these subcommands are
+optional:
+
+@display
+@t{/FORMAT}
+    [@t{MINCOLWIDTH=}@{@t{DEFAULT} @math{|} @i{width}@}]
+    [@t{MAXCOLWIDTH=}@{@t{DEFAULT} @math{|} @i{width}@}]
+    [@t{UNITS=}@{@t{POINTS} @math{|} @t{INCHES} @math{|} @t{CM}@}]
+    [@t{EMPTY=}@{@t{ZERO} @math{|} @t{BLANK} @math{|} @i{string}@}]
+    [@t{MISSING=}@i{string}]
+@t{/VLABELS}
+    @t{VARIABLES=}@i{variables}
+    @t{DISPLAY}=@{@t{DEFAULT} @math{|} @t{NAME} @math{|} @t{LABEL} @math{|} @t{BOTH} @math{|} @t{NONE}@}
+@t{/MRSETS COUNTDUPLICATES=}@{@t{YES} @math{|} @t{NO}@}
+@t{/SMISSING} @{@t{VARIABLE} @math{|} @t{LISTWISE}@}
+@t{/PCOMPUTE} @t{&}@i{category}@t{=EXPR(}@i{expression}@t{)}
+@t{/PPROPERTIES} @t{&}@i{category}@dots{}
+    [@t{LABEL=}@i{string}]
+    [@t{FORMAT=}[@i{summary} @i{format}]@dots{}]
+    [@t{HIDESOURCECATS=}@{@t{NO} @math{|} @t{YES}@}
+@t{/WEIGHT VARIABLE=}@i{variable}
+@t{/HIDESMALLCOUNTS COUNT=@i{count}}
+@end display
+
+The following subcommands follow @code{TABLE} and apply only to the
+previous @code{TABLE}.  All of these subcommands are optional:
+
+@display
+@t{/SLABELS}
+    [@t{POSITION=}@{@t{COLUMN} @math{|} @t{ROW} @math{|} @t{LAYER}@}]
+    [@t{VISIBLE=}@{@t{YES} @math{|} @t{NO}@}]
+@t{/CLABELS} @{@t{AUTO} @math{|} @{@t{ROWLABELS}@math{|}@t{COLLABELS}@}@t{=}@{@t{OPPOSITE}@math{|}@t{LAYER}@}@}
+@t{/CRITERIA CILEVEL=}@i{percentage}
+@t{/CATEGORIES} @t{VARIABLES=}@i{variables}
+    @{@t{[}@i{value}@t{,} @i{value}@dots{}@t{]}
+   @math{|} [@t{ORDER=}@{@t{A} @math{|} @t{D}@}]
+     [@t{KEY=}@{@t{VALUE} @math{|} @t{LABEL} @math{|} @i{summary}@t{(}@i{variable}@t{)}@}]
+     [@t{MISSING=}@{@t{EXCLUDE} @math{|} @t{INCLUDE}@}]@}
+    [@t{TOTAL=}@{@t{NO} @math{|} @t{YES}@} [@t{LABEL=}@i{string}] [@t{POSITION=}@{@t{AFTER} @math{|} @t{BEFORE}@}]]
+    [@t{EMPTY=}@{@t{INCLUDE} @math{|} @t{EXCLUDE}@}]
+@t{/TITLES}
+    [@t{TITLE=}@i{string}@dots{}]
+    [@t{CAPTION=}@i{string}@dots{}]
+    [@t{CORNER=}@i{string}@dots{}]
+@t{/SIGTEST TYPE=CHISQUARE}
+    [@t{ALPHA=}@i{siglevel}]
+    [@t{INCLUDEMRSETS=}@{@t{YES} @math{|} @t{NO}@}]
+    [@t{CATEGORIES=}@{@t{ALLVISIBLE} @math{|} @t{SUBTOTALS}@}]
+@t{/COMPARETEST TYPE=}@{@t{PROP} @math{|} @t{MEAN}@}
+    [@t{ALPHA=}@i{value}[@t{,} @i{value}]]
+    [@t{ADJUST=}@{@t{BONFERRONI} @math{|} @t{BH} @math{|} @t{NONE}@}]
+    [@t{INCLUDEMRSETS=}@{@t{YES} @math{|} @t{NO}@}]
+    [@t{MEANSVARIANCE=}@{@t{ALLCATS} @math{|} @t{TESTEDCATS}@}]
+    [@t{CATEGORIES=}@{@t{ALLVISIBLE} @math{|} @t{SUBTOTALS}@}]
+    [@t{MERGE=}@{@t{NO} @math{|} @t{YES}@}]
+    [@t{STYLE=}@{@t{APA} @math{|} @t{SIMPLE}@}]
+    [@t{SHOWSIG=}@{@t{NO} @math{|} @t{YES}@}]
+@end display
+
+The @code{CTABLES} (aka ``custom tables'') command produces
+multi-dimensional tables from categorical and scale data.  It offers
+many options for data summarization and formatting.
+
+This section's examples use data from the 2008 (USA) National Survey
+of Drinking and Driving Attitudes and Behaviors, a public domain data
+set from the (USA) National Highway Traffic Administration and
+available at @url{https://data.transportation.gov}.  @pspp{} includes
+this data set, with a slightly modified dictionary, as
+@file{examples/nhtsa.sav}.
+
+@menu
+* CTABLES Basics::
+@end menu
+
+@node CTABLES Basics
+@subsection Basics
+
+The only required subcommand is @code{TABLE}, which specifies the
+variables to include along each axis:
+@display
+@t{/TABLE} @i{rows} [@t{BY} @i{columns} [@t{BY} @i{layers}]]
+@end display
+@noindent
+In @code{TABLE}, each of @var{rows}, @var{columns}, and @var{layers}
+is either empty or an axis expression that specifies one or more
+variables.  An axis expression that names a categorical variable
+divides the data into cells according to the values of that variable.
+When all the variables named on @code{TABLE} are categorical, by
+default each cell displays the number of cases that it contains, so
+specifying a single variable yields a frequency table:
+
+@example
+CTABLES /TABLE=AgeGroup.
+@end example
+@psppoutput {ctables1}
+
+@noindent
+Specifying a row and a column categorical variable yields a
+crosstabulation:
+
+@example
+CTABLES /TABLE=AgeGroup BY qns3a.
+@end example
+@psppoutput {ctables2}
+
+@noindent
+The @samp{>} operator nests multiple variables on a single axis, e.g.:
+
+@example
+CTABLES /TABLE qn105ba BY AgeGroup > qns3a.
+@end example
+@psppoutput {ctables3}
+
+@noindent
+The @samp{+} operator allows a single output table to include multiple
+data analyses.  With @samp{+}, @code{CTABLES} divides the output table
+into multiple sections, each of which includes an analysis of the full
+data set.  For example, the following command separately tabulates age
+group and driving frequency by gender:
+
+@example
+CTABLES /TABLE AgeGroup + qn1 BY qns3a.
+@end example
+@psppoutput {ctables4}
+
+@noindent
+If @samp{+} and @samp{>} are used together, @samp{>} binds more
+tightly.  Use parentheses to override operator precedence.  Thus:
+
+@example
+CTABLES /TABLE qn26 + qn27 > qns3a.
+CTABLES /TABLE (qn26 + qn27) > qns3a.
+@end example
+@psppoutput {ctables5}
 
 @node FACTOR
 @section FACTOR
@@ -1403,19 +1567,19 @@ is used.
 
 
 @menu
-* BINOMIAL::                Binomial Test
-* CHISQUARE::               Chi-square Test
-* COCHRAN::                 Cochran Q Test
-* FRIEDMAN::                Friedman Test
-* KENDALL::                 Kendall's W Test
-* KOLMOGOROV-SMIRNOV::      Kolmogorov Smirnov Test
-* KRUSKAL-WALLIS::          Kruskal-Wallis Test
-* MANN-WHITNEY::            Mann Whitney U Test
-* MCNEMAR::                 McNemar Test
-* MEDIAN::                  Median Test
-* RUNS::                    Runs Test
-* SIGN::                    The Sign Test
-* WILCOXON::                Wilcoxon Signed Ranks Test
+* BINOMIAL::                    Binomial Test
+* CHISQUARE::                   Chi-square Test
+* COCHRAN::                     Cochran Q Test
+* FRIEDMAN::                    Friedman Test
+* KENDALL::                     Kendall's W Test
+* KOLMOGOROV-SMIRNOV::          Kolmogorov Smirnov Test
+* KRUSKAL-WALLIS::              Kruskal-Wallis Test
+* MANN-WHITNEY::                Mann Whitney U Test
+* MCNEMAR::                     McNemar Test
+* MEDIAN::                      Median Test
+* RUNS::                        Runs Test
+* SIGN::                        The Sign Test
+* WILCOXON::                    Wilcoxon Signed Ranks Test
 @end menu
 
 
@@ -1634,9 +1798,10 @@ arbitrary number of populations.  It does not assume normality.
 The data to be compared are specified by @var{var_list}.
 The categorical variable determining the groups to which the
 data belongs is given by @var{var}. The limits @var{lower} and
-@var{upper} specify the valid range of @var{var}. Any cases for
-which @var{var} falls outside [@var{lower}, @var{upper}] are
-ignored.
+@var{upper} specify the valid range of @var{var}.
+If @var{upper} is smaller than @var{lower}, the PSPP will assume their values
+to be reversed. Any cases for which @var{var} falls outside
+[@var{lower}, @var{upper}] are ignored.
 
 The mean rank of each group as well as the chi-squared value and
 significance of the test are printed.