Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: st: RE: overid with fixed effects
From
"Schaffer, Mark E" <[email protected]>
To
"[email protected]" <[email protected]>
Subject
RE: st: RE: overid with fixed effects
Date
Thu, 27 Feb 2014 21:24:57 +0000
Sorin,
Carlos is right. You can get an overidentification test statistic only if the model is overidentified. Yours is exactly identified.
--Mark
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Carlos Avellaneda Suárez
> Sent: 27 February 2014 20:34
> To: [email protected]
> Subject: Re: st: RE: overid with fixed effects
>
> My guess is that -overid- cannot run when only one instrumental
> variable is included in the model. You have to include 2 or more:
>
> webuse laborsup
>
> ivprobit fem_work kids (other_inc = male_educ), twostep
> overid
> Test of overidentifying restrictions:
> Amemiya-Lee-Newey minimum chi-sq statistic 0.000 Chi-sq(0) P-value = .
>
> ivprobit fem_work kids (other_inc = male_educ fem_educ ), twostep
> overid
> Test of overidentifying restrictions:
> Amemiya-Lee-Newey minimum chi-sq statistic 68.754 Chi-sq(1)
> P-value = 0.0000
>
> Hope this helps.
> Carlos
>
> 2014-02-27 14:58 GMT-05:00 Sorin Krammer <[email protected]>:
> > Dear Mark,
> >
> > Thank you for your reply and the suggestion.
> > I have re-run the regressions as suggested (i.e., without the omitted
> > regressors) but overid
> > still does not work properly. Regardless of specification, I get this
> > output:
> >
> > . overid
> >
> > Test of overidentifying restrictions:
> > Amemiya-Lee-Newey minimum chi-sq statistic 0.000 Chi-sq(0) P-value
> > = .
> >
> >
> > Any thoughts on this?
> >
> > Thank you.
> > Sorin
> >
> >
> > --------------------------------------------------------
> > Sorin,
> >
> >> -----Original Message-----
> >> From: [email protected] [mailto:owner-
> >> [email protected]] On Behalf Of Sorin Krammer
> >> Sent: 25 February 2014 10:18
> >> To: [email protected]
> >> Subject: st: overid with fixed effects
> >>
> >> Dear Stata-listers,
> >>
> >> I am having some trouble running the diagnostic tests (overid) after
> > IVprobit.
> >> Specifically, the overid command does not work, and I get the
> > following error
> >> message:
> >> "o. operator not allowed"
> >
> > The -overid- command is a bit long in the tooth, as they say, and
> > doesn't (yet) support the more modern Stata estimation output where
> > omitted variables are denoted internally using the "o." operator.
> >
> > The solution is to re-estimate but exclude the omitted regressors
> > dummysec18 and dummycountry30 from the estimation so that -ivprobit-
> > doesn't do it.
> >
> > --Mark
> >
> >>
> >> The dataset is a cross-section of firms, and the dummies represent country
> >> and sector fixed-effects.
> >>
> >> Below is the Stata output.
> >> Any help on solving this issue would be much appreciated.
> >>
> >> Thank you,
> >> Sorin
> >>
> >>
> >>
> >> ivprobit niperf (wibe =wibe_src12) lnsize age pfo manexp comp export rd
> >> finance dummysec* dummycountry*,twostep
> >>
> >> note: dummysec18 omitted because of collinearity
> >> note: dummycountry30 omitted because of collinearity Checking reduced-
> >> form model...
> >>
> >> Two-step probit with endogenous regressors Number of obs =
> >> 7938
> >> Wald chi2(55) =
> >> 1338.02
> >> Prob > chi2 =
> >> 0.0000
> >>
> >>
> > --------------------------------------------------------------------------------
> >> | Coef. Std. Err. z P>|z| [95% Conf.
> >> Interval]
> >> ---------------+--------------------------------------------------------
> >> ---------------+--------
> >> wibe | .0387125 .0099985 3.87 0.000 .0191157
> >> .0583092
> >> lnsize | .0578077 .012631 4.58 0.000 .0330514
> >> .082564
> >> age | -.0027215 .0012543 -2.17 0.030 -.00518
> >> -.0002631
> >> pfo | .2103776 .0621549 3.38 0.001 .0885563
> >> .332199
> >> manexp | .0020969 .0015714 1.33 0.182 -.000983
> >> .0051768
> >> comp | .1019847 .0149898 6.80 0.000 .0726053
> >> .1313641
> >> export | .2576724 .0436627 5.90 0.000 .1720951
> >> .3432498
> >> rd | .8353312 .0398095 20.98 0.000 .757306
> >> .9133565
> >> finance | .198445 .0329135 6.03 0.000 .1339357
> >> .2629544
> >> dummysec1 | -.2389516 .1515584 -1.58 0.115 -.5360007
> >> .0580975
> >> dummysec2 | -.1867943 .1518865 -1.23 0.219 -.4844863
> >> .1108977
> >> dummysec3 | -.4278744 .1681018 -2.55 0.011 -.7573478
> >> -.098401
> >> dummysec4 | -.3165274 .157684 -2.01 0.045 -.6255823
> >> -.0074725
> >> dummysec5 | -.1945854 .1701904 -1.14 0.253 -.5281524
> >> .1389816
> >> dummysec6 | -.3411836 .1876766 -1.82 0.069 -.709023
> >> .0266558
> >> dummysec7 | -.3226429 .1677384 -1.92 0.054 -.651404
> >> .0061182
> >> dummysec8 | .1094814 .2277545 0.48 0.631 -.3369093
> >> .5558721
> >> dummysec9 | -.2062024 .1605089 -1.28 0.199 -.5207941
> >> .1083893
> >> dummysec10 | -.2381757 .1661139 -1.43 0.152 -.5637531
> >> .0874016
> >> dummysec11 | -.2622814 .2081309 -1.26 0.208 -.6702105
> >> .1456477
> >> dummysec12 | -.7878382 .1517089 -5.19 0.000 -1.085182
> >> -.4904943
> >> dummysec13 | -.3522726 .1678885 -2.10 0.036 -.6813279
> >> -.0232172
> >> dummysec14 | -.0661616 .1527514 -0.43 0.665 -.3655488
> >> .2332255
> >> dummysec15 | -.1730415 .1460919 -1.18 0.236 -.4593764
> >> .1132933
> >> dummysec16 | -.3553452 .1616354 -2.20 0.028 -.6721447
> >> -.0385457
> >> dummysec17 | -.8712897 .1592536 -5.47 0.000 -1.183421
> >> -.5591584
> >> dummysec18 | 0 (omitted)
> >> dummycountry1 | -.9958689 .2308262 -4.31 0.000 -1.44828
> >> -.5434578
> >> dummycountry2 | .148311 .2040108 0.73 0.467 -.2515427
> >> .5481647
> >> dummycountry3 | -.7225869 .2001102 -3.61 0.000 -1.114796
> >> -.3303782
> >> dummycountry4 | -.3920646 .1965872 -1.99 0.046 -.7773684
> >> -.0067608
> >> dummycountry5 | -.8806025 .1808386 -4.87 0.000 -1.23504
> >> -.5261653
> >> dummycountry6 | -.30624 .187432 -1.63 0.102 -.6736001
> >> .0611201
> >> dummycountry7 | -1.038392 .1936603 -5.36 0.000 -1.41796
> >> -.6588251
> >> dummycountry8 | -.2388914 .1823388 -1.31 0.190 -.5962688
> >> .118486
> >> dummycountry9 | -.2357354 .1902911 -1.24 0.215 -.6086991
> >> .1372283
> >> dummycountry10 | -.6840301 .1928882 -3.55 0.000 -1.062084
> >> -.3059761
> >> dummycountry11 | -.3277489 .1918996 -1.71 0.088 -.7038652
> >> .0483674
> >> dummycountry12 | -.5434274 .1887301 -2.88 0.004 -.9133315
> >> -.1735233
> >> dummycountry13 | -.4139371 .1919193 -2.16 0.031 -.790092
> >> -.0377822
> >> dummycountry14 | -.5170694 .1949626 -2.65 0.008 -.899189
> >> -.1349498
> >> dummycountry15 | -.3960148 .1936286 -2.05 0.041 -.7755198
> >> -.0165098
> >> dummycountry16 | -.4731799 .1919085 -2.47 0.014 -.8493137
> >> -.0970461
> >> dummycountry17 | -.1953833 .1923881 -1.02 0.310 -.5724571
> >> .1816905
> >> dummycountry18 | -.6470639 .2079569 -3.11 0.002 -1.054652
> >> -.2394758
> >> dummycountry19 | .0195694 .1892384 0.10 0.918 -.3513309
> >> .3904698
> >> dummycountry20 | -.2873089 .1958224 -1.47 0.142 -.6711137
> >> .0964958
> >> dummycountry21 | -.1989027 .1984429 -1.00 0.316 -.5878436
> >> .1900383
> >> dummycountry22 | -.3685787 .2028177 -1.82 0.069 -.7660942
> >> .0289367
> >> dummycountry23 | -.8501975 .1924701 -4.42 0.000 -1.227432
> >> -.4729631
> >> dummycountry24 | -.2558144 .1994218 -1.28 0.200 -.646674
> >> .1350452
> >> dummycountry25 | .0587657 .1988078 0.30 0.768 -.3308904
> >> .4484218
> >> dummycountry26 | -.4283343 .2026821 -2.11 0.035 -.825584
> >> -.0310846
> >> dummycountry27 | -.040276 .1974263 -0.20 0.838 -.4272244
> >> .3466724
> >> dummycountry28 | -.8178818 .2064661 -3.96 0.000 -1.222548
> >> -.4132157
> >> dummycountry29 | -.4408704 .2133132 -2.07 0.039 -.8589566
> >> -.0227841
> >> dummycountry30 | 0 (omitted)
> >> _cons | .014316 .2313522 0.06 0.951 -.439126
> >> .467758
> >>
> > --------------------------------------------------------------------------------
> >> Instrumented: wibe
> >> Instruments: lnsize age pfo manexp comp export rd finance dummysec1
> >> dummysec2 dummysec3 dummysec4 dummysec5 dummysec6
> >> dummysec7
> >> dummysec8 dummysec9 dummysec10 dummysec11 dummysec12
> >> dummysec13
> >> dummysec14 dummysec15 dummysec16 dummysec17
> >> dummycountry1
> >> dummycountry2 dummycountry3 dummycountry4 dummycountry5
> >> dummycountry6 dummycountry7 dummycountry8 dummycountry9
> >> dummycountry10 dummycountry11 dummycountry12
> >> dummycountry13
> >> dummycountry14 dummycountry15 dummycountry16
> >> dummycountry17
> >> dummycountry18 dummycountry19 dummycountry20
> >> dummycountry21
> >> dummycountry22 dummycountry23 dummycountry24
> >> dummycountry25
> >> dummycountry26 dummycountry27 dummycountry28
> >> dummycountry29
> >> wibe_src12
> >>
> > --------------------------------------------------------------------------------
> >> Wald test of exogeneity: chi2(1) = 5.07 Prob > chi2 =
> >> 0.0244
> >>
> >> . overid, all
> >> o. operator not allowed
> >> r(101);
> >>
> >> *
> >> * 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/
> >
> >
> > -----
> > Sunday Times Scottish University of the Year 2011-2013
> > Top in the UK for student experience
> > Fourth university in the UK and top in Scotland (National Student Survey
> > 2012)
> >
> >
> > We invite research leaders and ambitious early career researchers to
> > join us in leading and driving research in key inter-disciplinary themes.
> > Please see www.hw.ac.uk/researchleaders for further information and how
> > to apply.
> >
> > Heriot-Watt University is a Scottish charity
> > registered under charity number SC000278.
> >
> >
> > *
> > * 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/
-----
Sunday Times Scottish University of the Year 2011-2013
Top in the UK for student experience
Fourth university in the UK and top in Scotland (National Student Survey 2012)
We invite research leaders and ambitious early career researchers to
join us in leading and driving research in key inter-disciplinary themes.
Please see www.hw.ac.uk/researchleaders for further information and how
to apply.
Heriot-Watt University is a Scottish charity
registered under charity number SC000278.
*
* 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/