Mark,
Many thanks for your suggestions. I have now tried tsset-ing the sample just
before starting boostrapping. But it still gives the same message.
Is there anyone else who has faced a similar problem with ivreg2?
Thanks,
Vidya
Dr Vidya Mahambare
B21, Cardiff Business School
Ph: 0044 29 2087 6407
>>> [email protected] 30/09/2004 16:51:32 >>>
Vidya,
I've never tried bootstrapping with a tsset dataset so I am at a loss
here. Maybe someone else on the list has suggestions?
The only thing I can think of is that you are tsset-ing once, at the
start of the process, and after the bootstrapping starts, that bit of
information gets cleared. The problem might go away if every call to
ivreg2 was preceded by a call to tsset.
If it doesn't, we might have to add a t() argument to ivreg2 that
forces it to use a specific variable as the time variable.
--Mark
Date sent: Thu, 30 Sep 2004 16:45:11 +0100
From: "Vidya Mahambare" <[email protected]>
To: <[email protected]>
Subject: Re: st: bootstrap ivreg2
Send reply to: [email protected]
> I did tsset time variable and ran ivreg2 to check if it is working. It
> worked fine. But doesn't seem to work when I try bootstrapping. It
> still says 'must tsset data and specify timevar'.
>
>
> thanks,
> Vidya
>
>
> >>> [email protected] 30/09/2004 16:39:53 >>>
> Vidya,
>
> ivreg2 needs to know about the time variable you are using in order to
> handle autocorrelation. You would get this error even if you ran one
> regression by hand - it's not related to bootstrapping.
>
> Try preceding the call to ivreg2 with
>
> tsset <your time variable>
>
> and see what happens.
>
> --Mark
>
> Date sent: Thu, 30 Sep 2004 16:32:43 +0100
> From: "Vidya Mahambare" <[email protected]>
> To: <[email protected]>
> Subject: st: bootstrap ivreg2
> Send reply to: [email protected]
>
> > Following Mark's reply I have now updated ivreg2 . Thanks.
> >
> > I am now trying to use -bootstrap- with ivreg2, but I keep getting
> > the following error message.
> >
> > insufficient observations to compute bootstrap standard errors
> > > no results will be saved
> > > r(2000);
> >
> > I supplied -bootstrap- with the -noisily- option to find out what is
> > the problem, which results in the error message -
> >
> > must tsset data and specify timevar
> > captured error running (ivreg2 r (lagr leadrpixg leadgdpg=.......
> >
> > I would appreciate any ideas on this.
> >
> > Is there another way to bootstrap GMM estimates for time series in
> > Stata?
> >
> >
> > Thanks
> > Vidya
> >
> >
> >
> >
> >
> >
> > *
> > * For searches and help try:
> > * http://www.stata.com/support/faqs/res/findit.html
> > * http://www.stata.com/support/statalist/faq
> > * http://www.ats.ucla.edu/stat/stata/
>
> Prof. Mark E. Schaffer
> Director
> Centre for Economic Reform and Transformation
> Department of Economics
> School of Management & Languages
> Heriot-Watt University, Edinburgh EH14 4AS UK
> 44-131-451-3494 direct
> 44-131-451-3008 fax
> 44-131-451-3485 CERT administrator
> http://www.som.hw.ac.uk/cert
>
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
Prof. Mark E. Schaffer
Director
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS UK
44-131-451-3494 direct
44-131-451-3008 fax
44-131-451-3485 CERT administrator
http://www.som.hw.ac.uk/cert
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
