Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Nahla Samargandi <Nahla.Samargandi@brunel.ac.uk> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | st: pmg &mg based on Hausman |
Date | Mon, 29 Aug 2011 13:23:09 +0100 |
Dear stata group, I could solve my previous problem regarding xtpmg. thanks for helping. and I have another question regarding Hausman test to compare between MG and PMG I run Hausman test below, and I would like firstly to make sure is this the right way to compare pmg with mg based on Hausman test, second, the p value I got is it indicate to the fails to reject the restriction of common long-run coefficecnts . Hence, the MG estimator is not as informative as the PMG estimator or the opposite ? third, how i can see the p value for each coefficient separately ? hausman mg pmg,sigmamore ---- Coefficients ---- | (b) (B) (b-B) sqrt(diag(V_b-V_B)) | mg pmg Difference S.E. -------------+---------------------------------------------------------------- L2.lntrade~p | -15.99317 6.072908 -22.06608 38.81535 education | -58.71332 -8.795231 -49.91809 67.2527 L.lnca | 60.09664 -2.920407 63.01705 44.75497 lngov | 7.75185 -3.248477 11.00033 67.8732 fd | -3.280872 2.16955 -5.450422 23.96994 ------------------------------------------------------------------------------ b = consistent under Ho and Ha; obtained from xtpmg B = inconsistent under Ha, efficient under Ho; obtained from xtpmg Test: Ho: difference in coefficients not systematic chi2(5) = (b-B)'[(V_b-V_B)^(-1)](b-B) = 3.34 Prob>chi2 = 0.6472 ( if this is > 0.05) (i.e insignificant use PMG ) Best regards * * 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/