Hi Allin,<br><br>thank your for this helpful feature!<br>Just as a side question. At the moment it seems not possible to access the break date; at least I haven&#39;t found a way to do so. If I am right, would it be possible to implement an accessor for this? Maybe by using the bundle-type syntax ($[&quot;garch_LR&quot;])?<br>
<br>Best,<br>Artur<br><br><div class="gmail_quote">2013/1/2 Allin Cottrell <span dir="ltr">&lt;<a href="mailto:cottrell@wfu.edu" target="_blank">cottrell@wfu.edu</a>&gt;</span><br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Something people might like to test: in CVS I&#39;ve added Bruce<br>
Hansen&#39;s asymptotic p-values for the &quot;qlrtest&quot; command, and also<br>
configured it so that if the original model was estimated with the<br>
--robust flag, the sup-Wald test uses the robust variance matrix.<br>
<br>
As for the issue I mentioned a week ago (the dating of the &quot;break&quot;),<br>
I notice that Hansen defines it the same way gretl does (the break<br>
period being the first period of the &quot;new regime&quot;) so I&#39;m not going<br>
to change that at present.<br>
<br>
Allin<br>
_______________________________________________<br>
Gretl-devel mailing list<br>
<a href="mailto:Gretl-devel@lists.wfu.edu">Gretl-devel@lists.wfu.edu</a><br>
<a href="http://lists.wfu.edu/mailman/listinfo/gretl-devel" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-devel</a><br>
</blockquote></div><br>