[Gmm-commits] r115 - in pkg/gmm: . R

[noreply at r-forge.r-project.org]

Author: chaussep
Date: 2017-08-24 15:12:41 +0200 (Thu, 24 Aug 2017)
New Revision: 115

Modified:
   pkg/gmm/NEWS
   pkg/gmm/R/gmm.R
Log:
added adjust=FALSE to vcovHAC in .myKernHAC

Modified: pkg/gmm/NEWS
===================================================================
--- pkg/gmm/NEWS	2017-08-22 20:34:16 UTC (rev 114)
+++ pkg/gmm/NEWS	2017-08-24 13:12:41 UTC (rev 115)
@@ -6,6 +6,8 @@
 o In previous versions, the HAC weighting matrix for linear models was computed without specifying that the first column of the
   instrument matrix was a column of ones (with its name being "(Intercept)"). It makes a difference when computing the bandwidth with
   bwNeweyWest. The new version, takes it into account. It is not possible to obtain the same sandwich covariance matrix with gmm and OLS.
+o In previous versions, the weighting matrix and, as a result, the standard errors were based on the small sample adjusted vcovHAC for weakly dependent
+  processes. The adjustment is not justified for GMM. The option adjust=FALSE is therefore added to vcovHAC in .myKernHAC()
 
 Changes in version 1.6-1
 

Modified: pkg/gmm/R/gmm.R
===================================================================
--- pkg/gmm/R/gmm.R	2017-08-22 20:34:16 UTC (rev 114)
+++ pkg/gmm/R/gmm.R	2017-08-24 13:12:41 UTC (rev 115)
@@ -124,7 +124,7 @@
                                   prewhite=AllArg$prewhite, tol=AllArg$tol)
 	w <- vcovHAC(x=gmat, order.by=AllArg$order.by, weights=weights,
                      prewhite=AllArg$prewhite, sandwich=FALSE,
-                     ar.method=AllArg$ar.method)
+                     ar.method=AllArg$ar.method, adjust=FALSE)
 	attr(w,"Spec") <- list(weights = weights, bw = AllArg$bw,
                                kernel = AllArg$kernel)
 	w