 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RE: reg ..., noc if... ?
Yes, that solves the problem. Thank you!
Chris
2009/8/13 Martin Weiss <[email protected]>:
>
> <>
>
>
> -If- qualifiers go before the comma, they are not part of the options, but a
> category in its own right...
>
> HTH
> Martin
>
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Stata Chris
> Sent: Donnerstag, 13. August 2009 21:00
> To: [email protected]
> Subject: st: reg ..., noc if... ?
>
> Dear Statalisters,
>
> I am using the following loop:
>
> gen beta = .
> gen se_beta = .
> gen t_beta = .
> forvalues i=456/515{
> capture noisily {
> reg delta L.delta if period==`i'
> replace beta = _b[L.delta] if period==`i'
> replace se_beta = _se[L.delta] if period==`i'
> replace t_beta = beta / se_beta if period==`i'
> }
> }
>
> Now I wanted to impose the constraint on each of the regressions that
> the constant should equal zero. However, if I add ",noc" (no
> constant), then Stata interprets everything after the comma as an
> option and tells me that "if period..." is not a valid option.
>
> So I was wondering if there is any way to have both the noc constraint
> and the if condition here?
>
> Many thanks, Chris
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/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/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/statalist/faq
* http://www.ats.ucla.edu/stat/stata/