cyy1985218 發(fā)表于 2011-7-20 13:31
xtreg tl size ndts tang tobin npr, fe
est store fe
xtivreg tl size ndts tang (npr=tobin L1.npr), fe
est store fe_iv
hausman fe fe_iv
這個(gè)檢驗(yàn)是P值為0,認(rèn)為存在內(nèi)生性,
這兩種檢驗(yàn)結(jié)果不同,到底應(yīng)該用哪種檢驗(yàn)呀
為什么在xtreg那邊有tobin,而在xtivreg那邊tobin被視為工具變數(shù)?
根據(jù)stata的幫助文件里提到
Davidson and MacKinnon (1993)
demonstrate that this test, which is similar to the (Durbin-Wu-)Hausman test
(see hausman) in this context, will always yield a computable test statistic,
whereas the Hausman test, depending on the difference of estimated covariance
matrices being a positive definite matrix, often cannot be computed by standard
matrix inverse methods.
因此除非是一些狀況下,否則兩者應(yīng)當(dāng)一樣,
我個(gè)人強(qiáng)烈懷疑,您在執(zhí)行Hausman test那邊變數(shù)擺法似乎有問題…