{smcl}
{* *! 24oct2006}{...}
{hline}
{cmd:help outsum}
{hline}

{title:Write formatted descriptive statistics to a text file}


{p 8 16 2}
{cmd:outsum} {varlist} {ifin} {weight} {helpb using} {it:filename} [{cmd:,} 
{opt ap:pend} {opt nol:abel} {opt nopa:ren} {opt br:acket} {opt nonob:s} {opt nonot:es} 
{opt replace} {opt com:ma} {opt quo:te} {opt ti:tle(textlist)} {opt ct:itle(textlist)} 
{opt addn:ote(textlist)}]

{p 4 6 2}
{opt aweight}s, {opt fweight}s and {opt iweight}s are allowed; see {help weight}.



{title:Description}

{pstd}
{opt outsum} writes means and standard deviations to an external text file, in 
much the same way {helpb outreg} produces formatted regression output, i.e. it
creates an ASCII text file with columns separated with tab characters and 
standard deviations displayed in parentheses below the means. The major 
difference is that the user must specify a {varlist} (using wildcards or 
hyphenated syntax) directly. As in {helpb outreg}, the {helpb using} clause specifies the
name of the new or existing ASCII file that will contain the means and 
standard deviations.

{pstd}
The options are largely the same as for {helpb outreg}.


{title:Options}

{phang}
{opt append} specifies that new descriptive statistic output be appended to an 
    existing output file. In general, the same {opt outsum} options should be used 
    in the original output and each appended column. The notes at the bottom 
    of the table explaining the standard deviations are correct for the 
    first column of descriptive statistics in the output file. If 
    subsequently appended results change the use of parentheses or brackets, 
    the notes will not be appropriate for all the columns. This problem can 
    be addressed with a combination of {opt nonotes} and {opt addnote}.

{phang}
{opt nolabel} specifies that variable names rather than variable labels be used to 
    identify coefficients.

{phang}
{opt noparen} specifies that no parentheses be placed around standard deviations.

{phang}
{opt bracket} specifies that square brackets [] be used rather than parentheses ()
    around standard deviations.

{phang}
{opt nonobs} specifies that the number of observations in the dataset not be 
    reported.

{phang}
{opt nonotes} specifies that notes explaining the standard deviations not be 
    included.

{phang}
{opt replace} specifies that it is okay to replace filename if it already exists.

{phang}
{opt comma} specifies that the ASCII file output be separated by commas rather than 
    by tabs. This can cause problems if any of the user-defined text has 
    commas in it (such as variable labels, {opt title}, {opt ctitle}, {opt addstat}, 
    or {opt addnote}). If that is the case, consider using {opt quote} as well.

{phang}
{opt quote} specifies that string variables be enclosed in double quotes.

{phang}
{opt title(textlist)} specifies a title or titles at the top of the regression 
    table. The maximum title length is 80 characters. Additional characters 
    will be cut off. When descriptive statistics are appended together, the 
    table title must be specified in the first outsum call; titles specified 
    in subsequent {opt outsum} {opt ... append} calls will be ignored. Note that when 
    converting the {opt outsum} text output to a table in a word processor or a 
    spreadsheet, it is easier to leave out the title row out of the text 
    selected for conversion.

{phang}
{opt ctitle(textlist)} specifies the title above the column of means and standard 
    deviations. By default if no column title is specified, the label or name 
    of the variable is displayed.

{phang}
{opt addnote(textlist)} specifies user-added notes to be displayed in new lines at 
    the bottom of the {opt outsum} table. When descriptive statistics are appended 
    together, {opt addnote} must be specified in the first {opt outsum} call; addnotes 
    specified in subsequent {opt outsum ... append} calls will be ignored. {opt addnote} 
    is consistent with {opt nonotes}. A blank line can be inserted by including "" 
    as a note.


{title:Examples}

{phang}{cmd:. use http://stata-press.com/data/r9/auto.dta, clear}

{phang}(1978 Automobile Data)

{phang}{cmd:. outsum mpg foreign weight using auto1, ctitle("Full sample")}

{phang}{cmd:. type auto1.out}

{txt:    Variable        Full sample}
{txt:    Mileage (mpg)   21.2973}
{txt:            (5.7855)}
{txt:    Car type        .2973}
{txt:            (.4602)}
{txt:    Weight (lbs.)   3019.459}
{txt:            (777.1936)}
{txt:    Observations    74}
{txt:    Standard deviations in parentheses  }

{phang}{cmd:. outsum mpg weight using auto1 if foreign==0, append ctitle("Domestic")}

{phang}{cmd:. type auto1.out}

{txt:    Variable        Full sample     Domestic}
{txt:    Mileage (mpg)   21.2973 19.8269}
{txt:            (5.7855)        (4.7433)}
{txt:    Car type        .2973   }
{txt:            (.4602) }
{txt:    Weight (lbs.)   3019.459        3317.115}
{txt:            (777.1936)      (695.3637)}
{txt:    Observations    74      52}
{txt:    Standard deviations in parentheses    }


{title:Author}

{psee}
Kerry L. Papps, Cornell University, USA

{pstd}
klp27@cornell.edu


{title:Also see}

{psee}
On-line:  {helpb outreg}, {helpb outsheet}