Recent posts by Pedro APhttps://sourceforge.net/u/albarran/2014-02-28T19:06:23Z#159 wrong use of exact distribution with robust estandard errors2014-02-28T19:06:23Z2014-02-28T19:06:23ZPedro APhttps://sourceforge.net/u/albarran/https://sourceforge.netc9919f7d0349879a107844d956b1638d64b36b15<div class="markdown_content"><p>There is a the very least a strong inconcruency in Gretl (and others): the same discussion above applies to Instrumental Variables estimators where only asymptotic distribution is known (normal for "t-ratios"). Normal distribution is, of course, used for p-values and even rename t-ratios to z-ratio to emphasize this. Why not using t-distributions if it is in practice equivalent to normal and conceptually not invalid? <br />
The point is that it is actually conceptually wrong (not an extreme possition, as in rigorous science things are right or not, beyond what the majority thinks) to claim that we know or we can approximate the exact distribution of IV (and OLS with Robust SE), so only claims about the known normal <em>asymptotic</em> distribution is used. </p>
<p>I felt that Gretl had the opportunity to do the things right, to make things clear and to be congruent (using the same criteria in two equivalent cases) beyond what others do and what in practice "just works". Maybe I was wrong in this point.</p></div>WikiPage Home modified by Pedro AP2012-12-02T16:07:56Z2012-12-02T16:07:56ZPedro APhttps://sourceforge.net/u/albarran/https://sourceforge.net1e32b338c5cfefcbdd6d10d590a4bd2ccf854f79Welcome to your wiki!
This is the default page, edit it as you see fit. To add a new page simply reference it within brackets, e.g.: [SamplePage].
The wiki uses [Markdown](/u/albarran/wiki/markdown_syntax/) syntax.
[[project_admins]]
[[download_button]]
optional use of asymptotic approximations2011-07-09T15:00:29Z2011-07-09T15:00:29ZPedro APhttps://sourceforge.net/u/albarran/https://sourceforge.net3ab8015a790d41598bb326c3d039f2bea28c36a5It would be nice that there was an option to choose asymptotic aproximations in testing output \(t-ratio, test for joint significance, Wald test of linear restriction, etc.\) instead of the exact statistics and distributions used to compute p-values under the normality assumption. One might want to use OLS without assuming normality in the same maner that one is not always willing to asume homoscedasticity or lack of serial correlation.
It would be the user choice to prefer believing in normality of errors or in asymptotic approximations in finite samplesoptional use of asymptotic approximations2011-07-09T15:00:29Z2011-07-09T15:00:29ZPedro APhttps://sourceforge.net/u/albarran/https://sourceforge.netdffeb5f6f59fe484ef636df5232e8eba090de157<div class="markdown_content"><p>Ticket 67 has been modified: optional use of asymptotic approximations<br />
Edited By: Sven S. (svetosch)<br />
Status updated: u'open' => u'closed'<br />
<em>milestone updated: '' => u'Next_Release</em>(example)'</p></div>wrong use of exact distribution with robust estandard errors2011-07-09T14:52:33Z2011-07-09T14:52:33ZPedro APhttps://sourceforge.net/u/albarran/https://sourceforge.net998bc38ccbf6f4f347e21393c965e905c13647baIt seems that current results when using robust standard errors display p-values computed from exact Student-t distributions. This is wrong since the exact distribution of OLS is unknown under heteroskedastity \(or serial correlation\). Then one can only use that t-ratios follow an asymptotic standard normal distribution. It would be also probably better to use the Wald statistic \(instead of the "robust" F statistc\) when testing linear restrictions.
wrong use of exact distribution with robust estandard errors2011-07-09T14:52:33Z2011-07-09T14:52:33ZPedro APhttps://sourceforge.net/u/albarran/https://sourceforge.net3fad787d47f21a9f8c2312f8cbb1adc61ce2ac53<div class="markdown_content"><p>Ticket 159 has been modified: wrong use of exact distribution with robust estandard errors<br />
Edited By: Sven S. (svetosch)<br />
Status updated: u'open' => u'closed-invalid'<br />
<em>milestone updated: '' => u'v1.0</em>(example)'</p></div>