Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Nick Cox <njcoxstata@gmail.com> |
| To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
| Subject | Re: st: GMM Newey-West HAC on quarterly time series data |
| Date | Thu, 22 Aug 2013 11:31:11 +0100 |
Good. By the way, your signature here "Aksom" suggests that your identifier "Aon na" is not your full real name. Please (re-)read the Statalist FAQ to see that use of full real names is requested. Nick njcoxstata@gmail.com On 22 August 2013 11:21, Aon na <mraon@hotmail.com> wrote: > Hi Nick > > It's work by using actest > > Many thanks for your help > Aksorn > ---------------------------------------- >> Date: Thu, 22 Aug 2013 11:07:06 +0100 >> Subject: Re: st: GMM Newey-West HAC on quarterly time series data >> From: njcoxstata@gmail.com >> To: statalist@hsphsun2.harvard.edu >> >> On 5) the write-up for -ivactest- (SSC) says, in effect, use -actest- >> (SSC) instead. That said, I can't comment on the specific problem >> here. >> Nick >> njcoxstata@gmail.com >> >> >> On 22 August 2013 10:57, Aon na <mraon@hotmail.com> wrote: >>> I employed GMM to deal >>> with price endogenous with three instruments by using >>> quarterly time series data (all 60 quarters) >>> >>> I would like to ask some questions. Since my data is quarterly time series that usually have autocorrelation problem . >>> >>> 1.) Can I run GMM and correct problem of autocorrelation and heteroscedasticity on my data with Newey-West >>> HAC variance? >>> >>> 2.) Is it correct if I used this command? (my priceb_s is endogenous) >>> ivreg2 lnsale1 (lnpriceb_s = lnwage lner lnppi) lngdp lnir lnbenzeneb policy , bw(4) gmm kernel(Bartlett) robust >>> >>> Can i use 4 in bw(4) because my data is quarterly time series? >>> >>> 3.) But if I use bw (1) both results of command give the similar results >>> >>> ivreg2 lnsale1 (lnpriceb_s = lnwage lner lnppi) lngdp lnir lnbenzeneb policy , bw(1) gmm kernel(Bartlett) robust >>> >>> ivregress gmm lnsale1 (lnpriceb_s = lnwage lner lnppi) lngdp lnir lnbenzeneb policy >>> >>> I am quite confused that both commands (ivreg2, gmm and ivregress gmm) are the same? >>> >>> 4.) After run the command, i try to check the autocorrelation by ivactest. I already install by command ssc install ivactest. >>> It had an error and say like this >>> >>> . ivactest >>> struct ms_vcvorthog undefined >>> (76 lines skipped) >>> (error occurred while loading ivactest.ado) >>> r(3000); >>> >>> Do I command correctly? >>> >>> Sorry for asking many questions. It would appreciate if someone could help. >>> Thank you very much >>> >>> * >>> * 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/ > > * > * 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/