Re: st: Time-series operators and -outreg-

[John Luke Gallup <jlgallup@pdx.edu>]

Jeremy,

-outreg- is an SSC user-written program (I wrote it :)).

A workaround to your problem is to use the -rtitles- option to enter the variable labels.  If you have just one independent variable (for example) named "varname" with variable label "Variable Name", then you would use the option -rtitles("Lagged Variable Name")-.

Another option is to create the lagged variables with -generate- instead of using the -l.- operator in the estimation command, and give the new variables variable labels.  Then -varlabel- will work as you expect.  The problem with using the -l.- operator in the estimation command is that you cannot assign a variable label to -l.varname- (as far as I know).

I do not apply the -varlabel- option to variables that have been lagged with the -l.- operator, because it is unclear how to label them consistently (how should I  distinguish -l.varname- from -l2.varname-) in a form the user is likely to want.

John

On May 2, 2013, at 8:32 AM, Jeremy Wells <jwell33@tigers.lsu.edu> wrote:

> I am using -outreg- (user-written, but not SSC, so I am not sure how
> exactly to describe it) to produce LaTeX tables from regression output.
> My regressions use lagged variables using the -l.- operator.
> 
> I used the -varlabels- option to replace variable names with labels, but
> unfortunately -outreg- prints "l.varname" for all the variables.
> 
> Is there a way to still get variable labels using time-series operators?
> 
> Thanks,
> 
> Jeremy Wells
> Ph.D. Student
> LSU Dept. of Poli. Sci.
> 324 Stubbs Hall
> Baton Rouge, LA 70803
> 
> 
> 
> 
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/