{smcl}
{* *! version 4.4 24dic2010}{...}
{cmd:help summout}
{hline}
{title:Title}
{phang}
{bf:summout} {hline 2} Comparative table of summary statistics
{title:Syntax}
{p 8 17 2}
{cmd:summout}
[{varlist}] {ifin} [using {it:filename}]{cmd:,} {opth "by(varname:groupvar)"} [{it:more options}]
{phang} {opt by} prefix is allowed; see {manhelp by D}.
{title:Description}
{pstd}{cmd:summout} creates a table of summary statistics for the variables listed in {it:varlist} across the categories of the categorical variable {it:groupvar}.
Output table can be copied and pasted into any worksheet using the "Copy Table" option of the right click menu.
In addition, it can be exported in ASCII format to the file indicated in {it:filename}.
This is useful for large tables or as part of .do files.
{pstd}
For every variable in {it:varlist}, {cmd:summout} first makes a normality test across the categories of {it:groupvar}.
If the test concludes normality, then mean and standard deviation are calculated, and a hypothesis test is done using {help oneway}.
If the test finds a non-normal distribution, then median, interquartile range and a {help kwallis:Kruskal-Wallis} test are shown instead.
{pstd}According to options, output table can have one or more of the following columns:
{phang}- Variable name or variable label{p_end}
{phang}- {bf:nonparam}, which is 0 if the tested variable has normal distribution and 1 if otherwise{p_end}
{phang}- {bf:est}: variable's estimate measure (mean or median) for specified category or total value{p_end}
{phang}- {bf:dis}: variable's dispersion measure (sd, se or iqr) for specified category or total value{p_end}
{phang}- {bf:lb}: variable's lower boundary of confidence interval for specified category or total value{p_end}
{phang}- {bf:ub}: variable's upper boundary of confidence interval for specified category or total value{p_end}
{phang}- {bf:p value}, indicating the p value of the corresponding hypothesis test{p_end}
{pstd}{cmd:summout} needs user-written command {help mat2txt}, please check if installed.
{title:Options}
{dlgtab:Main}
{phang}{opt by(groupvar)} is required, it indicates the variable containing the categories for comparison.
{it:groupvar} must have at least two values or an error message will be shown.
Same error will be displayed if population selected with {it:if} or {it:in} arguments leaves {it:groupvar} with only one category.
{phang}{opt ig:nore} causes {cmd:summout} to assume all variables as normal (use this at your own risk).
{phang}{opt se} diplays standard error of the mean instead of standard deviation (for normally distributed variables only).
{phang}{opt ci} calculates and displays confidence intervals instead of a dispersion measure.
Confidence intervals are calculated using {help ci} or {help centile} accordingly. Option {opt ci} overrides {opt se}.
{phang}{opt level(#)} sets confidence level; default is {opt level(95)}.
{phang}{opt dp(#)} specifies number of decimal places for estimate and dispersion measures; default is {opt dp(2)}.
{phang}{opt nt()} specifies normality test to be used: sk for {help sktest:Skewness and kurtosis test},
ks for {help ksmirnov:Kolmogorov-Smirnov test} and sw for {help swilk:Shapiro-Wilk test}. Default is {opt nt(sw)}.
{phang}{opt nol:abel} omits variable labels and value labels on the output table.
{title:Examples}
{bf:sysuse auto}
{bf:summout price mpg weight, by(foreign)}
{bf:summout price mpg weight, by(foreign) nt(sk)}
{bf:summout price mpg weight, by(foreign) nt(ks)}
{bf:summout price mpg weight, by(foreign) ignore}
{bf:summout price mpg weight, by(foreign) nolabel}
{bf:summout price mpg weight, by(foreign) se}
{bf:summout price mpg weight, by(foreign) dp(3)}
{bf:summout price mpg weight, by(foreign) ci level(99)}
{bf:summout price mpg weight using example.txt, by(rep78)}
{title:Acknowledgements}
{pstd}
Special thanks to Ian Watson (see inspirational command {help tabout:tabout}) for his valuable programming advice and to Zumin Shi for his constructive feedback.
{title:Author}
{phang}Andrés González Rangel{p_end}
{phang}MD, MSc Clinical Epidemiology{p_end}
{phang}Universidad Nacional de Colombia{p_end}
{phang}algonzalezr@unal.edu.co{p_end}