{smcl}
{* 17aug2014}{...}
{helpb outreg2}
{hline}
{title:Titles & related stuffs}
{p2colset 5 16 22 2}{...}
{p2col :{hi: outreg2} {hline 2}}Arrange regression, summary, and tabulation into an illustrative table{p_end}
{p2colset 5 15 20 2}{...}
{p2col :{hi: {help seeout}} {hline 2}}Opens a tab-delimited table in the data browser{p_end}
{p2colset 5 17 23 2}{...}
{p2col :{hi: {help shellout}} {hline 2}}Opens documents and their programs from inside Stata{p_end}
{p2colset 5 15 21 2}{...}
{p2col :{hi: {help logout}} {hline 2}}Converts log or ASCII files into various output formats{p_end}
{p2colset 5 14 20 2}{...}
{p2col :{hi: {help mkest}} {hline 2}}Convert variables to estimates matrix{p_end}
{title:Examples}
{help outreg2##s_0:0. Basic game plan}
{help outreg2##s_1:1. Prefix and -bys:-} {help outreg2##s_11:11. Marginal Effects}
{help outreg2##s_2:2. Running loops} {help outreg2##s_12:12. Word or Excel files}
{help outreg2##s_3:3. Stored estimates} {help outreg2##s_13:13. TeX files}
{help outreg2##s_4:4. Shorthand} {help outreg2##s_14:14. Adding column titles or notes}
{help outreg2##s_5:5. Decimal places} {help outreg2##s_15:15. n-way cross-tabulation}
{help outreg2##s_6:6. Sideway display} {help outreg2##s_16:16. Group summary table}
{help outreg2##s_7:7. Summary tables} {help outreg2##s_17:17. Fixed effects or legends}
{help outreg2##s_8:8. Drop/keep/order variables} {help outreg2##s_18:18. Stats transformation/manipulation}
{help outreg2##s_9:9. Adding r( ) e( ) scalars} {help outreg2##s_19:19. Matching policy variables}
{help outreg2##s_10:10. Odds ratios and rrr} {help outreg2##s_20:20. Insert r-class cmd( ) outputs}
{p 4 4 6}{help outreg2##s_FAQ:Frequently asked questions}{p_end}
{p 4 4 6}{help outreg2##s_Terms:Terms of Use}{p_end}
{p2colreset}{...}
{hline}
{marker s_Description}
{title:Description}
{p 4 4 6}
{cmd:outreg2} provides a fast and easy way to produce an illustrative table
of regression outputs. The regression outputs are produced piecemeal and are
difficult to compare without some type of rearrangement. {cmd:outreg2}
automates this process by concatenating the successive regression ouputs in a
vertical format. The resulting table is saved to the disk in ASCII
format, which can be read by other programs.
{p 4 4 6}
{cmd:outreg2} thus facilitates the convertion of regression outputs to a standard
format suitable for inclusion in a scholarly publication. The functionality of outreg2
is based on the earlier package {help cmd:outreg}, by John Gallup. {help outreg2##s_Differences:Unlike}
{cmd:outreg}, {cmd:outreg2} is capable of writing LaTeX-format tables, as well as ASCII, MS Word
and MS Excel.
{p 4 4 6}
{cmd:outreg2} can report any regression output, provided it conforms to
{it:the} {it:usual} {it:convention} for {help ereturn:ereturn list}. This includes
most regression commands in Stata 7 or later. {cmd:outreg2} will report the latest regression output
by default, or the list of {help estimates:stored estimates}. The ancillary statistics from from stored
{help return} can also be accessed using {opt e( )} or {opt adds:tat( )}.
{p 4 4 6}
{cmd:outreg2} will also report the usual statistics such as standard error with the asterisks for the levels of
significance (1%, 5%, and 10%), t-statistics, p-values, the number of observations,
R-squareds, and the number of groups in a panel estimation. Standarized beta
coefficients, exponentially transformed coefficients (i.e. odds/risk ratios
or hazard rate). The user can add their own column titles with {opt ct:itle} and {opt addn:ote} options.
{p 4 4 6}
An immediate access to the produced table is provided in the browser view with
{opt see} option. {cmd:outreg2} also comes with automatically formatted number of
significant digits, which avoids the awkward displays assoicated with the fixed
format.
{hline}
{marker s_Syntax}
{title:Syntax}
{synopt: Full syntax:}{p_end}
{p 6 8 6}
{cmdab:outreg2} [{varlist}] {cmd:[}{help estimates:{it:estlist}}{cmd:]}
{helpb using} {it:filename} [{cmd:,} {it:options}] [{cmd::} {help estimation commands:{it:command}}] {p_end}
{synopt: Shorthand:}{p_end}
{p 6 8 6}
{cmdab:outreg2} [{varlist}] {cmd:[}{help estimates:{it:estlist}}{cmd:]}
[{cmd:,} replace seeout]
[{cmd::} {help estimation commands:{it:command}}] {p_end}
{p 4 4 6}
where {it:command} takes one of {help estimation commands}. The shorthand works
only after a full syntax has been invoked.{p_end}
{p 4 6 2}
Note that {it:filename} must be enclosed within double quotes if it contains embedded spaces.{p_end}
{marker s_Options}
{title:Options}
{dlgtab:Main}
{phang}{opt replace} create a new file or overwrite the existing file.{p_end}
{phang}{opt see:out} display the regression table in the browser.{p_end}
{phang}{opt skip} skips a column (adds an empty column).{p_end}
{phang}{opt lab:el} replace variable names with variable labels, also see stats(label){p_end}
{phang}{opt lab:el( )} takes the following options for label:{p_end}
{p 8} {cmd:insert} - insert labels next to variable names{p_end}
{p 8} {cmd:proper} - proper cases (capitalize the first letter){p_end}
{p 8} {cmd:upper} - all upper cases{p_end}
{p 8} {cmd:lower} - all lower cases{p_end}
{phang}{opt side:way} specify sideway display (with standard error next to coefficient). Use {opt paren( )}
or {opt noparen} to control the location of parentheses.{p_end}
{phang}{opt long} interweave the equation names into the same column
with the variable names column, the default is usually wide. Also specify {opt text} if you want a converted text as well. {p_end}
{phang}{opt o:necol} specify one column to display multiple equations; the default is usually wide.{p_end}
{phang}{opt wide} forces wide format with multiple columns, rarely required.{p_end}
{dlgtab:Output Files}
{phang}{opt dta} produces Stata file. A suffix "_dta" is added to the file name to prevent the possible loss of main data.{p_end}
{phang}{cmd:dta(saveold)} produces in older Stata file format, as in {help saveold}.{p_end}
{phang}{opt word} produces rich text file (rft) compatible with {cmd:MS Word}. The file conversion can be
specified at any time (you should do it with the last appedning). The existing file must not be open for
it to be written over.{p_end}
{phang}{opt excel} specifies an xml, xls, xlm, or cvs file compatible with a standard spreadsheet
like {cmd:MS Excel}. Any existing file with the same name must be closed to have it
replaced with a new file.{p_end}
{phang}{opt tex} produces TeX output for a TeX typesetting program such as Scientific Word.{p_end}
{phang}{cmd:tex( )} takes the following options for tex:{p_end}
{p 8} {cmd:{ul:frag}}ment - a TeX fragment for inclusion in a document{p_end}
{p 8} {cmd:{ul:pr}}etty - with some italics and varying font sizes{p_end}
{p 8} {cmd:{ul:land}}scape - horizontally{p_end}
{phang}{opt text} produces plain text file exactly. {opt long} or {opt label} will
sometimes cause the main output text file to be different from what might be
expected. Use this option to obtain exactly specified text file.{p_end}
{phang}{opt quote} specifies quotation marks to encase each observation. See the {opt noquote}
option in {help outsheet} for more details (all the output of {cmd:outreg2} comes
from string variables). {opt quote} may cause problems appending tables together. {p_end}
{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 ct:itle}, {opt adds:tat}, or
{opt addn:ote}). If that is the case, consider using {opt quote} as well. {p_end}
{dlgtab:Statistics for each variable (main table)}
{phang}{opt st:ats(stats)} contains statistics to be reported per variable, the default is
{cmd:stats(coef se)}, space or comma separated, restricted to the estimation sample (single equation), will appear
in the order specified by the user:
{p 8 8 12}coef se tstat pval ci ci_low ci_high beta
{help summ:N} sum_w mean Var sd sum min max skewness kurtosis
p1 p5 p10 p25 p50 p75 p90 p95 p99
{help tabstat:range} iqr cv semean median count
{help corr} covar {help pcorr} {help pcorr2:semipcorr} pcorrpval
{help spearman} tau_a tau_b{p_end}
{p 8 8 12}eqname varname aster label label_pr label_up label_low blank{p_end}
{p 8 12 12}str({it:str}) where {it:str} is any string or numeric expression{p_end}
{p 17 17 12}internally stored and recalled as string1, string2, etc.{p_end}
{p 8 12 12}cmd({it:macro}: {it:cmd}) where {it:macro} is to be produced by {help outreg2##s_20:{it:cmd}}{p_end}
{p 24 24 12}internally stored and recalled as cmd1, cmd2, etc.{p_end}
{phang}{opt stnum(commands)} applies Stata or user-defined {help outreg2##s_18:commands} to {it:numerical} forms of the {cmd:stats( )},
use this option for mathematical/numeric operations, comma delimited, use quotes when there is a comma within a command,
usually limited to stats specified in {cmd:stats( )}, also see {cmd:ststr( )} below for string operations{p_end}
{phang}{opt ststr(commands)} applies Stata or user-defined {help outreg2##s_18:commands} to {it:string} forms of the {cmd:stats( )},
use this option to attach symbols or concatenate, comma delimited, use compound quotes if there is a comma in the command,
usually limited to stats specified in {cmd:stats( )}, also see {cmd:stnum( )} above{p_end}
{phang}{opt ef:orm} specifies coefficients to be reported. This corresponds to {opt or} option for
{help logit}, {help clogit}, and {help glogit} estimation, {opt irr} for {help poisson} estimation, {opt rrr}
for {help mlogit}, {opt hr} for {help cox} and {help stcox} hazard models, and
{opt eform} for {help xtgee}. The default form of {help stcox} is the hazard rate form; use the {opt eform} to report it. {p_end}
{phang}{opt l:evel(integer)} specifies the confidence level, in percent, for
confidence intervals. The default is {opt level(95)} or as set by {help set level},
does not affect the significance levels of asterisks. {p_end}
{p 4 8 8}{ul:Short-cut for auxillary statistics}{p_end}
{phang}{opt nose} specifies coefficients reported without std. errors{p_end}
{phang}{opt tstat} displays t-statistics under the coefficent{p_end}
{phang}{opt pvalue} displays p-values under the coefficent{p_end}
{phang}{opt ci} displays conf. intervals under the coefficent{p_end}
{phang}{opt be:ta} displays normalized beta coefficients (see the beta option of {help regress}){p_end}
{dlgtab:Significance}
{phang}{opt alpha(numlist)} specifies the levels of significance, separated by comma
from the most significant to the least signficiant. Example: {opt alpha(0.001, 0.01, 0.05)}. Up to 3 are automatically
assigned asterisks. If more than 3 levels are defined, then the symbols must be specified with {opt sym:bol(text)}. {p_end}
{phang}{opt sym:bol(text)} specifies symbols for the levels of significance from the most significant
to the least significant, the default {opt sym:bol(***, **, *)}. The significance levels of 0.01,
0.05, and 0.10 will be automatically assigned in that order. If more than 3 symbols are assigned, then the
same number of levels of significance must be specified using {opt alpha( )}.{p_end}
{phang}{opt aster:isk( )} specifies asterisks to be placed next to them; default {cmd:stats(coef)}.{p_end}
{phang}{opt noas:ter} no asterisks denoting statistical significance
levels be reported. {p_end}
{phang}{opt 2aster} specifies ** for 1% and * for 5% {p_end}
{phang}{opt 10pct} equivalent to {opt sym:bol(**, *, +)}{p_end}
{dlgtab:Decimals and Formats}
{phang}{opt auto(integer)} the number of automatically formatted decimals, the default is {cmd:auto(3)},
i.e. three significant digits not counting the ones (i.e. the digit to the left of the decimal point).
This means 1.234 and 0.123 might be displayed, while 12.345 or 0.1234 will be trimmed. A probable integer
is reported without decimals. A very large or small number will be displayed in
exponential format. Specify {opt dec( )} or {opt bd:ec( )} to disable it. {p_end}
{phang}{opt less(integer)} specifies how many less significant digits to be
displayed for the auxiliary (non-coefficient) statistics. The default is {cmd:less(0)}, meaning no less.{p_end}
{phang}{opt decm:ark( )} contains the decimal marker; default {opt decm:ark(.)}{p_end}
{phang}{ul:fixed decimals & formats}{p_end}
{opt dec(#)} or {opt fmt(type)} for everything, default {cmd:dec(3)} and {cmd:fmt(fc)}
{p 8}where # is fixed decimals between 0 and 11, {p_end}
{p 8}and {it:type} is one of the following:{p_end}
e exponential
f fixed
fc fixed with commas for thousands
g general
gc general with commas for thousands
Use the following only if you want them different from {opt dec(#)} or {opt fmt(type)}:
{opt bd:ec(#)} or {opt bf:mt(type)} for coefficient only
{opt sd:ec(#)} or {opt sf:mt(type)} for standard error
{opt td:ec(#)} or {opt tf:mt(type)} for t-statistics
{opt pd:ec(#)} or {opt pf:mt(type)} for p-value
{opt cd:ec(#)} or {opt cf:mt(type)} for conf. interval
{opt rd:ec(#)} or {opt rf:mt(type)} for r-square
{opt ad:ec(#)} or {opt af:mt(type)} for addstat( ) contents
{dlgtab:Titles and notes}
{phang}{opt ti:tle(list)} titles for your table; comma separated; use quotes for commas within a title.
Titles can be added at any time. To erase your title, encase a space between quotes like this: title(" "){p_end}
{phang}{opt ct:itle(list)} column titles; comma separated for each additonal row; semi-colon for each additional column;
use quotes if comma is part of title. Example: ctitle("Wage, Participation","Wage: Participation"). To specify empty column title, specify
ctitle(" ").{p_end}
{phang}{opt cttop(list)} place additonal column titles on the top; comma separated, use quotes for multiple column titles.{p_end}
{phang}{opt addn:ote(list)} add your own notes at the bottom. Must be specified in the first {cmd:outreg2}
call when regression results are appended together. A blank line can be inserted by including "" as a note.{p_end}
{phang}{opt nonot:es} specifies that notes and legends explaining the standard errors, asterisks, etc., not be included.{p_end}
{dlgtab:Parenthesis and brackets}
{phang}{opt par:en(stats)} specifies parenthesis ( ) to be placed around the same list as stats( ).{p_end}
{phang}{opt nopa:ren} specifies no parentheses be placed around standard
errors, t-statistics, standard errors, etc. {p_end}
{phang}{opt br:acket} specifies square brackets [ ] be used rather than
parentheses ( ) around standard errors, t-statistics, etc. {p_end}
{phang}{opt br:acket(stats)} specifies square brackets [ ] to be placed around the same list as stats( ).{p_end}
{dlgtab:Statistics for each regression (at bottom)}
{phang}{opt e(scalars)} reports {help ereturn:e-class scalars} at the bottom of the table.
They may be requested individually, as in {cmd:e(N ll r2)}, or for all, by specifying {cmd:e(all)}.
The reported e-class statistics are automatically formated by auto-digits, unless {opt ade:c}
has been specified for it. {p_end}
{phang}{opt adds:tat(name, stats, ..)} access {help ereturns:e-class}, {help return:r-class}, {help sreturn:s-class}
scalar statistics, or just plain numbers in new rows below the R-squared (if shown). Comma separted.
The user must specify both a name and a value for the statistic. See {help outreg2##s_9:example}.{p_end}
{phang}{opt addtext(name, text, ..)} specifies user-added text (including
numbers) to be displayed in new lines below the R-squared (if shown). Unlike {opt adds:tat},
{opt addt:ext} will not format numbers nor try to interpret any e-class text (such as e(N) or e(title)). {p_end}
{phang}{opt ad:jr2} specifies that the adjusted R-squared be reported rather than the regular R-squared
when available.{p_end}
{phang}{opt nocon:s} specifies that the intercept (constant) be not reported.
{phang}{opt noni} specifies that the number of groups in a panel data regression
not be reported (e.g. the number of groups specified by the i( ) variable in {help xtreg}).{p_end}
{phang}{opt nor:2} specifies that no R-squared (or adjusted R-squared) be reported.{p_end}
{phang}{opt noobs} specifies no number of observations is to be reported.{p_end}
{dlgtab:Equations and Variables}
{phang}{opt depvar} Include depdendent variable.{p_end}
{phang}{opt nodepvar} Attempt to drop depdendent variable.{p_end}
{phang}{opt policy(varlist)} {help outreg2##s_19:Match policy variables across regressions}.{p_end}
{phang}{opt drop(varlist)} Drop these variables. Do not include the dependent variable in this list.{p_end}
{phang}{opt keep(varlist)} Keep and report these variables. {p_end}
{phang}{opt eqdrop(eqlist)} Drop these equations from the table {p_end}
{phang}{opt eqkeep(eqlist)} Keep and report these equations. {p_end}
{phang}{opt sortvar(varlist)} Sort and order variables; non-existent variable names are ignored.{p_end}
{phang}{opt groupvar(names)} Sort and order variable; non-existent names are inserted as super-rows or row-heading.{p_end}
{dlgtab:Marginal effects}
{phang}{opt mfx} reports marginal effects as computed by {help mfx}. It will reported marginal
effects instead of estiamted coefficients. {p_end}
{phang}{opt m:argin(u|c|p)} the unconditional, conditional, and probability marginal
effects for {help truncreg}, {net_d:marginal} from STB 52, or {net_d:dtobit} from STB 56.
One of u, c, or p is required after {net_d:dtobit}, corresponding to the unconditional,
conditional, and probability marginal effects, respectively. It is not necessary to specify
{opt margin} after {help dprobit}, {net_d:dlogit2}, {net_d:dprobit2}, or {net_d:dmlogit2}.{p_end}
{dlgtab:Summary Statistics}
{phang}{opt sum} summary be reported after a regression command, restricted to the estimation sample, i.e. e(sample)==1,
unless no regress exists or {opt raw} option specified. This is the same as {cmd:stats(mean sd)}.{p_end}
{phang}{opt raw} do not restrict the sample to e(sample) or perform casewise dropping. Currently works only with sum.
The number of observation reported is the maximum.{p_end}
{phang}{cmd:sum(log)} summary table just like the one from log file. Default is raw (no casewise dropping).
Use eqdrop( ) or eqkeep( ) to get what you want.{p_end}
{phang}{cmd:sum(detail)} detailed summary table. Default is raw (no casewise dropping).
Use eqdrop( ) or eqkeep( ) to get what you want.{p_end}
{dlgtab:Tabulations}
{phang}{opt cross:tab} n-way cross-tabulation. Varlist is required. The first
variable must be counting numbers, i.e. 0, 1, 2, etc., and the rest must be non-strings. See {help outreg2##s_15:example} below. {p_end}
{dlgtab:Laptop/External/Network Drives}
{phang}{opt slow(#)} specifies # of milli-second delay. Specify slow(100) or larger if you are getting
"could not be openend r(603)" error; it's probably either (1) your storage device is running too slow, or
(2) you don't have write-access, in which case you need to change working directory
with {help cd}.{p_end}
{hline}
{marker s_0}
{title:Example 0. Basic game plan}
{p 4 4 6}You should specify the current directory where all the files will be stored. Alternatively, you
can specify the complete pathway from within {cmd:outreg2}, but you need to
encase it with quotations marks. {cmd:Either way, you must have write-access to that folder.} Otherwise you get r(603) error.{p_end}
{p 4 10 8}cd "C:\Users\yourname\Documents\" /* or whatever your directory may be */{p_end}
{p 4 10 8}{stata sysuse auto,clear}{p_end}
{p 4 10 8}{stata regress mpg foreign weight headroom trunk length turn displacement}{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace cttop(full)}{p_end}
{p 4 10 8}{stata regress mpg foreign weight headroom}{p_end}
{p 4 10 8}{stata outreg2 using myfile, see word excel tex dta}{p_end}
{p 4 4 6}You can immedicately see the changes. The variable "weight" loses some of its significance
in the full specification. The estimated effect of weight can be shown to be downward-biased from
-0.00420 to -0.00647 by omitting a number of covariates. This is an easy way to check for
collinearity and misspecification.{p_end}
{p 4 4 6}You can use {cmd:e( )} or {cmd:addstat( )} option to augment the standard
regression results with other e-class statistics (scalar only). {cmd:addstat} can handle
r-class and s-class results as well, if they exist. The following codes are equivalent
excpet in appearance.{p_end}
{p 4 10 8}{stata outreg2 using myfile, e(r2 ll)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, addstat(R-squared by hand, e(r2), Log Lik, e(ll))}{p_end}
{p 4 4 6}If you want to see everything available in the e-class, do it like this:{p_end}
{p 4 10 8}{stata outreg2 using myfile, e(all)}{p_end}
{marker s_1}
{title:Example 1. Prefix and -bys:-}
{p 4 4 6}{cmd:outreg2} can be used in as a prefix.{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata "outreg2 using myfile, replace ti(Car stuff): reg price mpg weight turn"}{p_end}
{p 4 10 8}{stata "outreg2 using myfile, see excel: reg price mpg weight turn if price > 6100"}{p_end}
{p 4 8 8}It is also byable with -bys:- prefix.{p_end}
{p 4 10 8}{stata "bys foreign: outreg2 using myfile, side replace see: reg rep78 head weight gear length turn [aw=mpg]"}{p_end}
{marker s_2}
{title:Example 2. Running loops}
{p 4 4 6}Because this involves a loop, you must copy and paste into a do-file:
{p 4 4 6}sysuse auto,clear{p_end}
{p 4 4 6}cap erase myfile.txt{p_end}
{p 4 4 6}forval num=1/5 {{p_end}
{p 8 8 6}regress mpg weight headroom if rep78==`num'{p_end}
{p 8 8 6}outreg2 using myfile{p_end}
{p 4 4 6}}{p_end}
{p 4 4 6}seeout{p_end}
{p 4 4 6}Alternatively, make use of macro{p_end}
{p 4 4 6}local replace replace{p_end}
{p 4 4 6}forval num=1/5 {{p_end}
{p 8 8 6}regress mpg weight headroom if rep78==`num'{p_end}
{p 8 8 6}outreg2 using myfile, `replace' {p_end}
{p 8 8 6}local replace{p_end}
{p 4 4 6}}{p_end}
{marker s_3}
{title:Example 3. Stored estimates}
{p 4 4 6}You can automatically recall the stored estimates by specifying them from
within {cmd:outreg2}. To distinguish them from the varlist, place the estlist
within a pair of {cmd:[}square brackets{cmd:]}.{p_end}
{p 4 10 8}{stata sysuse auto,clear}{p_end}
{p 4 10 8}{stata regress mpg foreign weight headroom trunk length turn displacement}{p_end}
{p 4 10 8}{stata est store Full}{p_end}
{p 4 10 8}{stata regress mpg foreign weight headroom}{p_end}
{p 4 10 8}{stata est store Restricted1}{p_end}
{p 4 10 8}{stata regress mpg foreign weight}{p_end}
{p 4 10 8}{stata est store Restricted2}{p_end}
{p 4 10 8}{stata outreg2 [Full Restricted1 Restricted2] using myfile, replace see}{p_end}
{p 4 4 6}{cmd:outreg2} will take the stored estimates as wildcards (*). Try this:
{p 4 10 8}{stata outreg2 [*] using myfile, see replace}{p_end}
{p 4 10 8}{stata outreg2 [R*] using myfile, see replace}{p_end}
{p 4 4 6}The varlist may be combined with the estlist. The varlist will take the
wildcards as well, provided they exist in the estlist.{p_end}
{p 4 10 8}{stata outreg2 foreign weight [*] using myfile, see replace}{p_end}
{p 4 4 6}If you are specifying the varlist, you must make certain the desired varlist
exists in all the stored estiamtes. Since not all equations may contain the
specified varlist, it is usually a poor idea to combine the one column option
with the varlist.{p_end}
{marker s_4}
{title:Example 4. Shorthand}
{p 4 4 6}{cmd:outreg2} will remeber the last set of options you specified until the end of
the day. The stored command will expire at mid-night to prevent the possible
loss of finished table by inadvertantly writing over a finished file. The
following shorthand should be tried separately.{p_end}
{p 4 10 8}{stata outreg2}{p_end}
{p 4 10 8}{stata outreg2, replace}{p_end}
{p 4 10 8}{stata outreg2, seeout}{p_end}
{p 4 4 6}The following two options are excluded from the stored command:
seeout and replace. These two must be specified each time you invoke {cmd:outreg2}
through the shorthand. To change the stored options, you must invoke the full
syntax with the specified using file (i.e. outreg2 using myfile, etc). The varlist
and the stored estimates names are not stored with the command.{p_end}
{p 4 4 6}For someone who is in a hurry, {cmd:outreg2} will take the following syntax, provided
the desired options have been stored by invoking them in the full syntax. The
varlist and/or the estlist are still allowed under this syntax. This
pre-command syntax is made available for the benefit of iterative users.{p_end}
{p 4 10 8}{stata "outreg2 : reg mpg foreign weight headroom"}{p_end}
{p 4 10 8}{stata "outreg2, replace : reg mpg foreign weight headroom"}{p_end}
{p 4 10 8}{stata outreg2}{p_end}
{p 4 10 8}{stata seeout}{p_end}
{marker s_5}
{title:Example 5. Decimal places}
{p 4 4 6}By default the regression coefficients are shown with auto-digits,
but a user may wish to specify their own number of decimals places. We could use
the option dec(5) to display 5 decimal places for all statistics or bdec(5)
for just the coefficient, sdec(5) just for standard error, etc.{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace auto(4)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, dec(5)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, bdec(5) bfmt(f) sdec(7) sfmt(e) see}{p_end}
{marker s_6}
{title:Example 6. Sideway display}
{p 4 4 6}Medical journals often requires the displays to go sideways. Use {opt side:way} to make this
happen. {opt side:way} is compatible with {opt st:ats( )}.
{p 4 10 8}{stata outreg2 using myfile, sideway stats(coef aster se) noparen dec(3) replace}{p_end}
{p 4 4 6}Note the above code is equivalent to building the table one column at a time like this:{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(coef) replace noparen dec(3)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(aster) noparen dec(3)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(se) noparen dec(3)}{p_end}
{p 4 4 6}Some journals often prefer t-statistics to standard errors
and don't use asterisks to denote statistical significance. Some people use brackets. The
title( ) option requires quotation marks when it contains a comma. Note that {opt dec} decimal
option apply to both the coefficients and the standard errors.{p_end}
{p 4 10 8}{stata regress mpg foreign weight}{p_end}
{p 4 10 8}{stata outreg2 using myfile, tstat bracket noaster title("No standard errors!")}{p_end}
{p 4 10 8}{stata seeout}{p_end}
{marker s_7}
{title:Example 7. Summary tables}
{p 4 4 6}Use {opt sum} to place summary statistics into a table. The sample mean and the standard
deviation for the sample used in the earlier regression will be automatically displayed.
{p 4 6 6}* After estimation{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata reg mpg price rep weight length}{p_end}
{p 4 10 8}{stata outreg2 using myfile, sum replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile, see}{p_end}
{p 4 6 6}* Regular summary table{p_end}
{p 4 6 6}* note: version 11 and above requires clear* to prevent mismatch between e(b) and e(sample){p_end}
{p 4 10 8}{stata clear*}{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata outreg2 using myfile, sum(log) replace eqdrop(N mean) see}{p_end}
{p 4 10 8}{stata outreg2 using myfile, sum(detail) replace eqkeep(N max min) see}{p_end}
{p 4 10 8}{stata outreg2 using myfile, sum(detail) replace see}{p_end}
{marker s_8}
{title:Example 8. Drop/keep/order variables}
{p 4 4 6}Specifying a varlist can be convenient to limit the output
table to only the essential coefficients. For example, we may want to control for
the influence of dummy variables, but not report their estimated coefficients.{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata tab rep78, gen(repair)}{p_end}
{p 4 10 8}{stata regress mpg foreign weight repair1-repair4}{p_end}
{p 4 10 8}{stata outreg2 weight foreign using myfile, drop(repair*)}{p_end}
{p 4 4 6}Alternatively, {opt keep( )} and {opt drop( )} can be used to control the displayed
variables. Use {opt nocons} to drop constants.
{p 4 10 8}{stata outreg2 using myfile, drop(repair*) replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile, keep(mpg foreign)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, nocons}{p_end}
{p 4 10 8}{stata seeout}{p_end}
{p 4 4 6}There are several ways to order variables in the output. The first is
to order them when running regression. The second way is to specify varlist
from within {cmd:outreg2}. Or you might try {opt sortvar( )} or {opt groupvar( )}.{p_end}
{p 4 6 6}* single equation{p_end}
{p 4 10 8}{stata reg mpg rep78 head trunk weight}{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace sortvar(trunk turn)}{p_end}
{p 4 10 8}{stata reg mpg rep78 head weight turn disp gear}{p_end}
{p 4 10 8}{stata outreg2 using myfile, sortvar(trunk turn) see}{p_end}
{p 4 6 6}* multiple equations{p_end}
{p 4 10 8}{stata reg3 (mpg rep78 head trunk weight) (head trunk weight rep78 gear)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace long}{p_end}
{p 4 10 8}{stata reg3 (mpg rep78 head weight turn disp ) (mpg rep78 head trunk weight gear)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, sortvar(trunk turn) see long}{p_end}
{p 4 6 6}* groupvar( ) will create super-rows{p_end}
{p 4 10 8}{stata reg mpg rep78 head trunk weight}{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace}{p_end}
{p 4 10 8}{stata reg mpg rep78 head weight turn disp gear}{p_end}
{p 4 10 8}{stata outreg2 using myfile, groupvar(Group1 trunk turn head weight Group2) see}{p_end}
{marker s_9}
{title:Example 9. Adding r( ) e( ) scalars}
{p 4 4 6}Additional statistics may be added with {opt adds:tat( )} or {opt addt:ext( )}. Values stored in
macros r( ), e( ), or s( ) can be included directly. You can see what values are available by typing
{cmd:ereturn list} or {cmd:return list}.{p_end}
{p 4 4 6}To test the equality of two of the estimated coefficients and report the results in the table, note
that {cmd:test} will sometimes return chi-squared, then you would instead use {opt addstat(chi-square test, r(chi2))}:
{p_end}
{p 4 10 8}{stata reg mpg foreign weight length}{p_end}
{p 4 10 8}{stata test foreign length}{p_end}
{p 4 10 8}{stata `"outreg2 using myfile, adds(F-test, r(F), Prob > F, `r(p)') replace"'}{p_end}
{p 4 10 8}{stata seeout} {p_end}
{p 4 4 6}To add results of lincom postestimation command to a table:{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata reg price mpg rep78 head}{p_end}
{p 4 10 8}{stata lincom mpg + rep}{p_end}
{p 4 10 8}{stata local tstat=r(estimate)/r(se)}{p_end}
{p 4 10 8}{stata local pval = tprob(r(df), abs(`tstat'))}{p_end}
{p 4 10 8}{stata outreg2 using "myfile", adds(joint, r(estimate), t-stat, `tstat', p-val,`pval') replace see}{p_end}
{p 4 4 6}In some cases it is better to save the value of a previously calculated
statistic in a local macro and then put that into {opt adds:tat( )}:{p_end}
{p 4 10 8}{stata regress mpg rep78 headroom}{p_end}
{p 4 10 8}{stata test rep78}{p_end}
{p 4 10 8}{stata local F1 = r(F)}{p_end}
{p 4 10 8}{stata test headroom}{p_end}
{p 4 10 8}{stata outreg2 using 2test, addstat(Test1 F, `F1', Test2 F, `r(F)')}{p_end}
{p 4 4 6}If it is missing, {cmd:outreg2} will automatically calculate e(p), which is presumably
the F-test or chi-square-test of significance of a regression.{p_end}
{p 4 10 8}{stata outreg2 using myfile, addstat(F test, e(p))}{p_end}
{p 4 4 6}Another example would be to report a pseudo R-squared
after a logit estimation, which {cmd:outreg2} does not otherwise report.{p_end}
{p 4 10 8}{stata logit foreign price trunk weight}{p_end}
{p 4 10 8}{stata outreg2 using myfile, addstat(Pseudo R-squared, `e(r2_p)')}{p_end}
{marker s_10}
{title:Example 10. Odds ratios and exponentials}
{p 4 4 6}Odds ratios are exponential transformations of coefficients. As noted above,
there is no way of knowing after an estimation command if the
user chose to report the exponentiated form of coefficients. The user must
choose the {opt eform} option in {cmd:outreg2} to get the same form of the coefficients
displayed by the estimation into the {cmd:outreg2} table.{p_end}
{p 4 4 6}For duration models, the exponential form is known as the hazard ratio. For
other models it is known as odds ratio, relative risk ratio, or incidence rate
ratio.{p_end}
{p 4 10 8}{stata sysuse auto,clear}{p_end}
{p 4 10 8}{stata logit foreign price mpg rep78, or}{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace cti(raw)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, eform cti(odds ratio) see}{p_end}
{p 4 6 6}* Alternatively:{p_end}
{p 4 8 6}{stata outreg2 using myfile, stnum(replace coef=exp(coef), replace se=coef*se) cti(odds ratio) see}{p_end}
{p 4 4 6}Note that coef was first transformed, then used to calculate se in the example above.{p_end}
{marker s_11}
{title:Example 11. Marginal Effects}
{p 4 4 6}{opt mfx} option can be used to report marginal effects after {help mfx} command
has been applied.{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata logit foreign mpg rep78 head}{p_end}
{p 4 10 8}{stata mfx compute}{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile, mfx ctitle(mfx) see}{p_end}
{p 4 4 6}{cmd:margins} will report it as well.{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata logit foreign mpg rep78 head}{p_end}
{p 4 10 8}{stata margins, dydx(_all) post}{p_end}
{p 4 10 8}{stata outreg2 using myfile, ctitle(margins) see}{p_end}
{p 4 4 6}For multiple outcomes, you may want to use {cmd:mfx2} by Ricahrd Williams or
{search margeff} by Tamas Bartus. They are both available from {help ssc}. {p_end}
{p 4 4 6}{cmd:margeff} example:{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata mlogit rep turn mpg price}{p_end}
{p 4 10 8}{stata margeff, at(mean) replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile, cttop(margeff) see replace}{p_end}
{p 4 4 6}{cmd:mfx2} runs a little slower:{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata mlogit rep turn mpg price}{p_end}
{p 4 10 8}{stata mfx2, replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile, long cttop(mfx2) see replace}{p_end}
{p 4 4 6}The marginal effects reported by {search dprobit}, {net_d:dlogit2}, {net_d:dprobit2},
and {search dmlogit2} are automatically reported by {cmd:outreg2}.{p_end}
{p 4 4 6}Because {net_d:truncreg}, {net_d:marginal}, and {net_d:dtobit} report
both regression coefficients and marginal effects, the user must specify the
{opt margin} option for {cmd:outreg2} report the marginal effects.{p_end}
{p 4 4 6}{search dtobit}, on the other hand, calculates three different marginal effects.
The user must specify which marginal effect, the unconditional, conditional,
or the probability uncensored, to be reported. Note that "version 6" must be set for
{cmd:dtobit} to work.{p_end}
{p 4 10 8}{stata `"version 6: tobit mpg trunk weight, ll(17)"'}{p_end}
{p 4 10 8}{stata `"version 6: dtobit"'}{p_end}
{p 4 10 8}{stata outreg2 using myfile, margin(u) ctitle(Unconditional) nor2 replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile, margin(c) ctitle(Conditional) nor2}{p_end}
{p 4 10 8}{stata outreg2 using myfile, margin(p) ctitle(Probability) nor2 see}{p_end}
{marker s_12}
{title:Example 12. Word or Excel files}
{p 4 4 6}
Use {opt word} or {opt excel} for automatic generation of Word/Excel files:
{p 4 10 8}{stata reg price mpg rep78 headroom trunk weight}{p_end}
{p 4 10 8}{stata outreg2 using myfile, word excel replace}{p_end}
{p 4 4 6}
Follow these directions for manual conversions from .txt files:
{p 4 4 6}
In {cmd:MS Word}, open or insert the file created by {cmd:outreg2}. Select the estimation text that
is in columns (not the notes at the bottom of the table or the title at the top, if any), and choose
Table, Convert Text to Table.
{p 4 4 6}To shift the table within {cmd:MS Word}, highlight the entire table, choose Table
Properties (go the top menu, drag down on the Table option), and then click the alignment as
Left instead of Center.
{p 4 4 6}
In {cmd:Excel}, open the file created by {cmd:outreg2} and follow the default choices
in the Text Import Wizard (if you do not see the file, choose All Files as the File Type).
Prevent the conversion of the parenthesis into a negative number (an accounting convention)
by doing the following: 1. import it as "Delimited", 2. choose Tab as the Delimiters, and
3. Choose "Text" as Column data format after Highlighting all the columns by shift-down, right-clicking.
{p 4 4 6}To export the .xml table to a word processor, you should separately copy the table and the notes
at the bottom of the table (prevents the notes from taking up too much space). You
can avoid this problem by opening the .txt file manually from inside {cmd:MS Excel},
as detailed earlier, or copy and paste the notes into another cells in
{cmd:MS Excel}, which will cause them to be displayed properly.
{p 4 4 6}To get rid of "green tabs" in Excel: From inisde Excel, Tools > Options > Error Checking.
When you get there, uncheck "Number stored as text". No more green triangles.
{p 4 4 6}
You can also use {cmd:{browse "http://www.stata.com/support/faqs/data/convert2.html":Stat/Transfer}}
if you have one. Choose ASCII-Delimited as the input file and choose {cmd:Excel}
as the output file. You will need to adjust the column widths from inside
{cmd:Excel}.
{marker s_13}
{title:Example 13. TeX files}
{p 4 4 6}
{cmd:LaTeX} compatible table can be created with {opt tex} option. With the use
of free conversion software, such as MiKTeX, you can create Adobe PDF files of
the finished tables directly within Stata by invoking a shell command.
{p 4 10 8}{stata regress mpg foreign weight}{p_end}
{p 4 10 8}{stata outreg2 using myfile, tex replace}{p_end}
{p 4 4 6}Free TeX-to-PDF conversion software are available, such as the MiKTeX (www.miktek.org) for
Windows or teTeX (www.tug.org/teTeX/) for Unix/Linux. They can be invoked with a shell command:{p_end}
{p 4 10 8}{stata !texify -p -c -b --run-viewer myfile.tex} {using MiKTeX on Windows){p_end}
{p 4 10 8}{stata !pdflatex myfile} (using teTeX on Linux){p_end}
{p 4 4 6}{cmd:outreg2} cannot append TeX format tables to one another, so regressions must be
appended in ASCII form until the last regression, which is appended with the
{opt tex} option.{_end}
{p 4 4 6}The base font point size of tex in a TeX table can be specified with the {opt tex( )}
parameter. TeX only allows font sizes of 10 and 11 points besides the default
of 12 point. The {opt texfrag} option creates a TeX fragment for inclusion in a larger
TeX document. For example, a TeX fragment table from the first regression above could be created with
{p 4 10 8}{stata outreg2 using myfile, tex(frag)}{p_end}
{p 4 4 6}and then be included in the following TeX document with the \input{myfile}
command:{p_end}
\documentclass[10pt]{article}
\begin{document}
... text before inclusion of table myfile.tex ...
\input{myfile}
... text after inclusion of table myfile.tex ...
\end{document}
{p 4 4 6}Technical Note: Non-alphanumeric characters often have special meaning
in TeX, namely _, %, #, $, &, ~, ^^, \, {, }. To print them like any other
character, include a \ in front of the character. {cmd:outreg2} automatically does this for
the first two, _ and %. You can include the other characters in titles,
variable labels, or notes if you preceed them with with a \ in the Stata text.
The exception is \ itself; \ must be replaced with $\backslash$ to render
properly in TeX.
{p 4 4 6}In addition, in TeX the characters <, >, and | will only appear as themselves
in math mode, so they must be written as $<$, $>$, and $|$.{p_end}
{p 4 4 6}TeX codes can be inserted into {cmd:outeg2} titles, variable labels, and added
notes. This requires understanding TeX formatting codes. The example below
creates a Greek letter chi with a squared exponent for a chi-squared test
statistic.{p_end}
{p 4 10 8}{stata outreg2 using myfile, addstat($\chi^2$, 22.1) tex}{p_end}
{p 4 4 6}Note that outreg2 will automatically convert < or > but not chi^2.{p_end}
{p 4 10 8}{stata `"outreg2 using myfile, addstat(LR $\chi^2$, e(chi2), Prob < $\chi^2$, e(p)) tex"'}{p_end}
{p 4 4 6}{cmd:outreg2} automatically converts _ to \_, except
when it finds two $'s in the text, in which case it assumes the _ is a
subscript designator in a TeX inline equation. That means that if you want to
add text that includes an inline equation, but you really want the _ to appear
as such in the TeX table, you must replace it with a \_.{p_end}
{p 4 4 6}Stata will interpret $ immediately followed by a letter as a global macro. To
get Stata to output a literal $, insert an escape character "\" like this: \$.
R-squared, for example, must be "\$R^2$" rather than "$R^2$" because $R would be evaluated
as the value of global macro R.{p_end}
{p 4 4 6}Putting a literal "$" in TeX output can be confusing: to get "$US" in the TeX
output, for example, one needs "\$US" in the TeX input file, which requires
"\\\$US" in Stata text, because Stata resolves "\\" into "\" and "\$" into "$".{p_end}
{p 4 4 6}A final quirk: you cannot use the results of the Stata macro $S_FN in {cmd:outreg2}
text for a TeX table if you use Microsoft Windows. $S_FN returns the path name
for the current data file which in Windows includes \ characters which will
prevent the TeX table from rendering properly.{p_end}
{marker s_14}
{title:Example 14. Adding column titles or notes}
{p 4 4 6}You can add a column title "Base case (mpg)" to distinguish this regression from a
second regression. No quotation marks are required around the column title because
it does not contain commas. Use {opt cttop( )} to add additional column title to the default column titles.{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace ctitle(Base case (mpg))}{p_end}
{p 4 10 8}{stata outreg2 using myfile, cttop(On top)}{p_end}
{p 4 4 6}You can add explanatory note at the bottom of a column using the {opt addn:ote} option.
Note that since the text in {opt addn:ote} does not contain parentheses or commas
it does not need quotation marks.{p_end}
{p 4 10 8}{stata outreg2 using myfile, addnote(Dummy variables not shown)} {p_end}
{p 4 4 6}{opt addnote} for inserting a blank line, followed by the time the program was run (from the
built-in Stata functions $S_TIME and $S_DATE), and the dataset used by the
estimation (from the Stata function $S_FN).{p_end}
{p 4 10 8}{stata regress mpg foreign weight length}{p_end}
{p 4 10 8}{stata `"outreg2 using myfile, addn("", "Time $S_TIME, $S_DATE", Data from $S_FN) replace"'} {p_end}
{marker s_15}
{title:Example 15. n-way cross-tabulation}
{p 4 4 6}n-way tabulation likes of which are also produced by tab3way or table. It will take about a minute to run.{p_end}
{p 4 6 6}* Prepare data{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata egen mileage=cut(mpg), group(10)}{p_end}
{p 4 10 8}{stata egen paid=cut(price), group(3)}{p_end}
{p 4 10 8}{stata egen heavy=cut(weight), group(3)}{p_end}
{p 4 6 6}* 3-way cross-tabulation sideway{p_end}
{p 4 10 8}{stata outreg2 mileage paid heavy using myfile, see replace cross side}{p_end}
{p 4 6 6}* 5-way cross-tabulation without percentage{p_end}
{p 4 10 8}{stata outreg2 mileage paid foreign rep78 heavy using myfile, see replace cross stats(coef)}{p_end}
{marker s_16}
{title:Example 16. Group summary table}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata gen white=cond(uniform( )>.5,1,0)}{p_end}
{p 4 10 8}{stata gen black=cond(white==1,0,1)}{p_end}
{p 4 10 8}{stata gen male=cond(uniform( )>.5,1,0)}{p_end}
{p 4 10 8}{stata gen female=cond(male==1,0,1)}{p_end}
{p 4 8 8}* do it with -bys:-{p_end}
{p 4 10 8}{stata `"bys male black: outreg2 using myfile, sum(log) eqkeep(mean N) drop(white female male black) excel replace"'}{p_end}
{p 4 8 8}* do it by hand{p_end}
{p 4 10 8}{stata outreg2 using myfile if white==1 & male==1, sum(log) eqkeep(mean N) cttop(white, male) drop(white male female) excel replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile if white==1 & female==1, sum(log) eqkeep(mean N) cttop( , female) drop(white male female) excel}{p_end}
{p 4 10 8}{stata outreg2 using myfile if white==1, sum(log) eqkeep(mean N) cttop( , total) drop(white male female) excel}{p_end}
{p 4 10 8}{stata outreg2 using myfile if black==1 & male==1, sum(log) eqkeep(mean N) cttop(black, male) drop(white male female) excel}{p_end}
{p 4 10 8}{stata outreg2 using myfile if black==1 & female==1, sum(log) eqkeep(mean N) cttop( , female) drop(white male female) excel}{p_end}
{p 4 10 8}{stata outreg2 using myfile if black==1, sum(log) eqkeep(mean N) cttop( , total) drop(white male female) excel}{p_end}
{marker s_17}
{title:Example 17. Fixed effects or legends}
{p 4 4 6}Two-way fixed-effects estimation with dummy indicators:{p_end}
{p 4 6 6}* set up data{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata ren rep78 state}{p_end}
{p 4 10 8}{stata ren turn id}{p_end}
{p 4 10 8}{stata keep id price mpg weight state}{p_end}
{p 4 10 8}{stata tab state, gen(ST)}{p_end}
{p 4 6 6}* regress and report{p_end}
{p 4 10 8}{stata xtreg price mpg weight ST*, fe i(id)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace drop(ST*) addtext(State FE, YES, Year FE, YES)}{p_end}
{p 4 10 8}{stata xtreg price mpg weight ST*, fe i(id)}{p_end}
{p 4 10 8}{stata outreg2 using myfile, drop(ST*) addtext(State FE, NO, Year FE, YES)}{p_end}
{p 4 10 8}{stata reg price mpg weight ST*}{p_end}
{p 4 10 8}{stata outreg2 using myfile, drop(ST*) addtext(State FE, NO, Year FE, NO)}{p_end}
{p 4 6 6}* legend{p_end}
{p 4 10 8}{stata outreg2 using myfile, st(str(Coef) str(Stn Err) str(Spearman)) noparen ct(Legend) replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile, st(coef se spearman blank)}{p_end}
{marker s_19}
{title:Example 19. Matching policy variables across regressions}
{p 4 10 8}The following matches the variables of interest as "Policy" and their names in the column title.{p_end}
{p 4 10 8}sysuse auto, clear{p_end}
{p 4 10 8}local replace replace{p_end}
{p 4 10 8}foreach var in length turn displacement {{p_end}
{p 4 10 8}reg price weight gear_ratio foreign `var'{p_end}
{p 8 10 8} outreg2 using this, `replace' policy(`var') sortvar(Policy) {p_end}
{p 8 10 8} local replace {p_end}
{p 4 10 8}}{p_end}
{marker s_18}
{title:Example 18. Stats transformation/manipulation}
{p 4 4 6}The contents of {cmd:stats( )} can be manipuated with standard Stata commands.{p_end}
{p 4 4 6}Use {opt stnum( )} to work with {it:numerical} forms.{p_end}
{p 4 4 8}* multiply by 100{p_end}
{p 4 10 8}{stata sysuse auto, clear}{p_end}
{p 4 10 8}{stata reg mpg price weight}{p_end}
{p 4 10 8}{stata outreg2 using myfile, replace}{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(coef se) stnum(replace coef=coef*100, replace se=se*100)}{p_end}
{p 4 4 8}* exponentiate both coef and se{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(coef se) stnum(replace coef=exp(coef), replace se=coef*se)}{p_end}
{p 4 4 8}* absolute value of t-statistics{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(coef tstat) stnum(replace tstat=abs(tstat))}{p_end}
{p 4 4 6}Use {opt ststr( )} to apply {it:string} operations.{p_end}
{p 4 4 8}* add dollar-sign ($) for the mean of price{p_end}
{p 4 10 8}{stata reg mpg price weight}{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(mean) ststr(replace mean="$"+mean if varname=="price") replace}{p_end}
{p 4 4 8}* add "max" to maximum and "min" to minimum{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(max min) ststr(replace max="max "+max if max~="", replace min="min "+min if min~="")}{p_end}
{p 4 4 6}Use {opt stnum( )} and {opt ststr( )} together.{p_end}
{p 4 4 8}* multiply by 100 and add percent (%) sign{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(mean) stnum(replace mean=mean*100) ststr(replace mean=mean+" %" if mean~="")}{p_end}
{p 4 6 6}* You can automate this process by writing your own programs and inserting them like this:{p_end}
{p 4 10 8}prog drop _all{p_end}
{p 4 10 8}prog define percent{p_end}
{p 8 12 10} replace mean=mean*100{p_end}
{p 4 10 8}end{p_end}
{p 4 10 8}prog define symbol{p_end}
{p 8 12 10} replace mean=mean+" %" if mean~=""{p_end}
{p 4 10 8}end{p_end}
{p 4 10 8}outreg2 using myfile, stats(mean) stnum(percent) ststr(symbol){p_end}
{p 4 4 8}* To manipuate string based on numerical content, generate a numerical copy in stnum( ):{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(mean) stnum(gen temp=mean) ststr(replace mean="Positive" if temp>0)}{p_end}
{p 4 4 8}* To concatenate (currently works only with major statistics, i.e. coef, se, tstat, etc.:{p_end}
{p 4 10 8}{stata outreg2 using myfile, stats(coef) ststr(replace coef=coef+" "+se) noaster}{p_end}
{marker s_20}
{title:Example 20. Insert r-class cmd( ) outputs}
{p 4 4 6}You can insert output from r-class command in the table body through cmd( : ) sub-option. Indep and dependent
variables will be fed to them.{p_end}
{p 4 6 6}* outputs Kendall's tau-a and tau-b{p_end}
{p 4 4 6}sysuse auto, clear{p_end}
{p 4 4 6}reg rep78 headroom length turn gear_ratio{p_end}
{p 4 10 8}outreg2 using myfile, replace stats(corr, spearman, cmd(r(tau_a): ktau), /*{p_end}
{p 12 12 8}*/cmd(r(tau_b): ktau)){p_end}
{p 4 6 6}* double-check{p_end}
{p 4 4 6}ktau rep78 headroom{p_end}
{p 4 4 6}ret list{p_end}
{p 4 4 6}{ul:Write and insert your own r-class output}
{p 4 4 6}You can write your own r-class program and insert their outputs. A scalar should be returned
on two inputs: independent variable and dependent variable. It needs to accept [if] syntax.
c_local programs will work, too, but there might be a conflict.{p_end}
{p 4 6 6}* r-class program that calculates coefficient of variation{p_end}
{p 4 4 6}cap prog drop coefvar{p_end}
{p 4 4 6}prog define coefvar, rclass{p_end}
{p 8 8 8}syntax varlist(max=2) [if]{p_end}
{p 8 8 8}gettoken dep indep : varlist{p_end}
{p 8 8 8}qui sum `indep' `if'{p_end}
{p 8 8 8}local variation=`r(sd)'/`r(mean)'*100{p_end}
{p 8 8 8}ret scalar variation=`variation'{p_end}
{p 4 4 6}end{p_end}
{p 4 6 6}* test your r-class program{p_end}
{p 4 4 6}sysuse auto, clear{p_end}
{p 4 4 6}reg rep78 headroom length turn gear_ratio{p_end}
{p 4 4 6}coefvar rep78 headroom if e(sample){p_end}
{p 4 4 6}ret list{p_end}
{p 4 6 6}* run them{p_end}
{p 4 4 6}sysuse auto, clear{p_end}
{p 4 4 6}reg rep78 headroom length turn gear_ratio{p_end}
{p 4 4 6}outreg2 using myfile, replace stats(coef, se, sd, cmd(r(variation): coefvar)){p_end}
{p 4 6 6}* return c_local instead of r-class scalar{p_end}
{p 4 4 6}cap prog drop coefvar2{p_end}
{p 4 4 6}prog define coefvar2{p_end}
{p 8 8 8}syntax varlist(max=2) [if], [proportion]{p_end}
{p 8 8 8}gettoken dep indep : varlist{p_end}
{p 8 8 8}qui sum `indep' `if'{p_end}
{p 8 8 8}local hundred 100{p_end}
{p 8 8 8}if "`proportion'"=="proportion" {{p_end}
{p 12 12 8}local hundred 1{p_end}
{p 8 8 8}}{p_end}
{p 8 8 8}local variation=`r(sd)'/`r(mean)'*`hundred'{p_end}
{p 8 8 8} c_local variation=`variation'{p_end}
{p 4 4 6}end{p_end}
{p 4 6 6}* run them{p_end}
{p 4 4 6}sysuse auto, clear{p_end}
{p 4 4 6}reg rep78 headroom length turn gear_ratio{p_end}
{p 4 4 6}outreg2 using myfile, stats(coef, se, sd, cmd(variation: coefvar2, proportion)){p_end}
{title:Send one to the e-mail address below}
{p 4 4 6}Programs like these can made into a sub-option for inclusion the future versions.
Please note that it should be something of interest to other people.{p_end}
{hline}
{title:How to report a possible error}
{p 4 4 6}1. it's best if you send an example using -sysuse- or -webuse- data{p_end}
{p 4 4 6}2. create a trace log file containing the error{p_end}
{p 4 4 6}3. Send them to whoever wrote the thing and ask nicely.{p_end}
cap log close
log using mylog.txt, text replace
which outreg2 /* or whatever command you are dealing with */
cret list
sysuse auto, clear /* or whatever data you are using */
reg rep78 trunk turn foreign /* or whatever you are doing */
set trace on
outreg2 using myfile, replace /* or whatever that gets you the error */
log close
{hline}
{marker s_FAQ}
{title:Frequently asked questions}
{p 4 7 8}Q: Why isn't adoupdate working with {helpb outreg2}?{p_end}
{p 4 7 8}A: Stata will refuse to update a package if it is incorrectly dated, i.e., backdated at the SSC.
This has been fixed. To force it to update, you would had to uninstall first (scc uninstall outreg2).{p_end}
{p 4 7 8}Q: How do I report the first-stage from {helpb ivregress}?{p_end}
{p 4 7 8}A: This has been the most frequently asked question with outreg2. What had been requested was a full
compatibility with the rest of Stata, i.e., factor variables, post estimation commands, etc. This was impletemented
for the first time by {helpb ivregress2}, which was the first to extend the official version in about 5 or 6 years.{p_end}
{p 4 7 8}Q: What error is "could not be openend r(603)"?{p_end}
{p 4 7 8}A: That usually comes up if you don't have write-acces to the folder. Use -cd- to change the pathway.{p_end}
{p 4 7 8}Q: Should I use LaTeX?{p_end}
{p 4 7 8}A: You are probably better off with Word/Adobe conversion to pdf. Most people do it that way.
LaTeX is great if you actually write lots of equations or white papers - only a small percentage of Stata users do that.{p_end}
{p 4 7 8}Q: Can I use Stata with Excel? Windows? {p_end}
{p 4 7 8}A: Virutally all empirical researchers use Excel. Stata grew up with PC. Microsoft Office is currently the
defacto standard in academia. I am not sure why this was an issue.{p_end}
{marker s_Terms}
{title:Terms of use}
{p 4 4 6}In my experience economists, particularily health economists, are very generous with their time
and resources. We often share codes and data sets, some of which are very rare and valuable. We do this out of
a sense of professional obligation or desire to help facilitate research. We don't do this to provide material to someone
with a long history of shifting through existing programs, claiming something is not needed after he extracted
seomthing from it. The program is free to use but may not be republished under false pretense. That is not a part
of acceptable use.{p_end}
{title:Author}
{p 4 4 6}Roy Wada{p_end}
{p 4 4 6}roywada@hotmail.com{p_end}
{title:Acknowledgements}
{p 4 4 6}outreg2 is based on the earlier works by John Luke Gallup john_gallup@alum.swarthmore.edu{p_end}
{p 4 4 6}codes from pcorr2 by Richard Williams have been incorporated for stats( ) suboption.{p_end}
{title:Also see}
{p 3}STB: sg97 (STB-46, STB-49, STB-58){p_end}
{p}Manual: {bf:[U] Estimation and post-estimation commands}{p_end}
{p 9}{bf:[U] Overview of model estimation}{p_end}
{p 9}{bf:[R] Estimation commands}{p_end}
{p }Online: {help est}, {help postfile}, {help outfile}, {help outsheet}, {help save},
{search modltbl}, {search desrep} {p_end}
{s6hlp}
{smcl}