Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Lim Boon Leong" <lboonl@streamyx.com> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: Individual and Joint Variables Orthogonality Test |
Date | Mon, 8 Mar 2010 17:55:00 +0800 |
Dear Statalists, I have four included exogenous variables that I wish to carry out the orthogonality test by using the orthog(varlist_ex) option of xtivreg2. I carry out the test for each of these 4 variables individually and one of the variables turn out not to be exogenous. Test results are shown below: -orthog- option: Hansen J statistic (eqn. excluding suspect orthog. conditions): 1.875 Chi-sq(5) P-val = 0.8661 C statistic (exogeneity/orthogonality of suspect instruments): 4.406 Chi-sq(1) P-val = 0.0358 Instruments tested: ceodual ---------------------------------------------------------------------------- -- Instrumented: ownexr ownex2r ownex3r L.ldiv L.debt Included instruments: ceodual ined remcom1 extblock1 L.lmktbk L.roa L.ret L.ltotasset yr04 yr05 yr06 Excluded instruments: lrisk lsale lsale2 ks ks2 ys ik L2.ldiv L.roe L.ltangible L2.debt Dropped collinear: yr02 yr03 yr07 The C statistic shows that ceodual cannot be treated as exogenous and actually it is endogenous. But when I carry out this orthog test for all the four variables jointly, I obtain the following results: -orthog- option: Hansen J statistic (eqn. excluding suspect orthog. conditions): 0.260 Chi-sq(2) P-val = 0.8779 C statistic (exogeneity/orthogonality of suspect instruments): 6.020 Chi-sq(4) P-val = 0.1976 Instruments tested: ceodual ined remcom1 extblock1 ---------------------------------------------------------------------------- -- Instrumented: ownexr ownex2r ownex3r L.ldiv L.debt Included instruments: ceodual ined remcom1 extblock1 L.lmktbk L.roa L.ret L.ltotasset yr04 yr05 yr06 Excluded instruments: lrisk lsale lsale2 ks ks2 ys ik L2.ldiv L.roe L.ltangible L2.debt Dropped collinear: yr02 yr03 yr07 ---------------------------------------------------------------------------- -- The C statistic shows that all of them are exogenous variables. My question is which test result should I follow, the individual or joint test results? And I am having difficulty in finding valid and relevant instruments for ceodual if it is treated as endogenous variable when applying two stage least square. Thank you in advance. Best regards, Boon Leong * * 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/