Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Christopher Baum <kit.baum@bc.edu> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | Re: st: Question about tesitng coefficients in the cointegrating equation with the VEC command |
Date | Mon, 14 Apr 2014 10:51:54 +0000 |
<> Bob asked I used the vec command to estimate a VEC model using two variables, y and z= . The output for the cointegrating equation is given below: Identification: beta is exactly identified Johansen normalization restriction imposed - ---------------------------------------------------------------------------= - --- beta | Coef. Std. Err. z P>|z| [95% Conf. Interv= al] - -------------+-------------------------------------------------------------= - --- _ce1 | y | 1 . . . . = . z | -.9929304 .0072861 -136.28 0.000 -1.007211 -.9786= 499 _cons | -.0816624 . . . . = . - ---------------------------------------------------------------------------= - --- I want to test whether the coefficient on z =3D -1. That seems fairly straightforward, if you're just trying to do the equivalent of a Wald test on the beta vector. Someone asked me privately how to test two coefficients in the vector for equivalence. clear webuse rdinc vec ln_ne ln_se ln_fw mata: beta = st_matrix("e(beta)") vce = st_matrix("e(V_beta)") beta vce // test equality of coefficients on se, fw z = (beta[2]-beta[3]) / sqrt(vce[2,2] + vce[3,3] - 2 * vce[2,3]) pval = 1 - normal(abs(z)) "test stat" z "p-value" pval end Kit Baum Professor of Economics and Social Work, Boston College, Chestnut Hill MA, USA DIW Research Professor, Department of Macroeconomics, DIW Berlin, Berlin, Germany baum@bc.edu | http://ideas.repec.org/e/pba1.html * * 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/