From: Daniel Schlieper <daniel@tuxomania.net>
Date: Sun, 7 Dec 2014 17:31:34 +0000 (-0800)
Subject: doc: Describe how bin sizes are chosen for histograms.
X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?p=pspp;a=commitdiff_plain;h=af3d2be249020c55e0e90925ff3b21fc70501bac

doc: Describe how bin sizes are chosen for histograms.
---

diff --git a/doc/statistics.texi b/doc/statistics.texi
index 7a880d15ab..9cc49557ea 100644
--- a/doc/statistics.texi
+++ b/doc/statistics.texi
@@ -195,9 +195,13 @@ For instance, @subcmd{/NTILES=4} would cause quartiles to be reported.
 The @subcmd{HISTOGRAM} subcommand causes the output to include a histogram for
 each specified numeric variable.  The X axis by default ranges from
 the minimum to the maximum value observed in the data, but the @subcmd{MINIMUM}
-and @subcmd{MAXIMUM} keywords can set an explicit range.  Specify @subcmd{NORMAL} to
-superimpose a normal curve on the histogram.  Histograms are not
-created for string variables.
+and @subcmd{MAXIMUM} keywords can set an explicit range. The number of
+bins are 2IQR(x)n^-1/3 according to the Freedman-Diaconis rule.  (Note that
+@cmd{EXAMINE} uses a different algorithm to determine bin sizes.)
+Histograms are not created for string variables.
+
+Specify @subcmd{NORMAL} to superimpose a normal curve on the
+histogram.
 
 @cindex piechart
 The @subcmd{PIECHART} subcommand adds a pie chart for each variable to the data.  Each
@@ -289,6 +293,10 @@ normal distribution, whilst the spread vs.@: level plot can be useful to visuali
 how the variance of differs between factors.
 Boxplots will also show you the outliers and extreme values.
 
+@subcmd{HISTOGRAM} uses Sturges' rule to determine the number of
+bins, as approximately 1 + log2(n).  (Note that @cmd{FREQUENCIES} uses a
+different algorithm to find the bin size.)
+
 The @subcmd{SPREADLEVEL} plot displays the interquartile range versus the 
 median.  It takes an optional parameter @var{t}, which specifies how the data
 should be transformed prior to plotting.