Article From: Department of Economics
Subject: LMDE.SET

Posted by: Information Provider
Phone Number: (202) 885-3770
E-Mail Address: econ@american.edu

Post Date: 28 Sep 1994
Expiration Date: 28 Oct 2004


               LMDE.SET (Ogaki)

@ LMDE.SET @    @ This file is for Version 2 of GAUSS @
/* Linear Minimum Distance Estimation (MDE)
For nonlinear MDE, use GMMQ.SET with tend=1;

Min (bp-dfb*bm)'invpd(COVbp)*(bp-dfb*bm)
 b
1. INPUT
   bp:    k by 1 vector, initial estimates
   w0: k by k invpd(COV(bp))
   dfb:   k by p matrix

2. OUTPUT
    lmde proc returns
   chi: chi-square test statistic for the linear restrictions.
    lmde proc saves
   bm
   varbm

*/

proc lmde(bp,w0,dfb);
local varbm,bm,chi,k,p,df;
?"**** Linear Minimum Distance Estimation (LMDE.SET) ****";
varbm=invpd(dfb'w0*dfb);
bm=varbm*(dfb')*w0*bp;
chi=(bp-dfb*bm)'w0*(bp-dfb*bm);
k=rows(dfb);
p=cols(dfb);
df=k-p;
save bm;
save varbm;
"bm=" bm';
"se=" sqrt(diag(varbm))';
"chi=" chi "(" df cdfchic(chi,df) ")";
retp(chi);
endp;

************************************************************************
Department of Economics is entirely responsible for the information
provided above. Please direct any comments to Information Provider at:
          E-Mail Address: econ@american.edu
          Phone Number:   (202) 885-3770