Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: VEC: t- instead of z-statistics


From   Richard Williams <richardwilliams.ndu@gmail.com>
To   statalist@hsphsun2.harvard.edu, statalist@hsphsun2.harvard.edu
Subject   Re: st: VEC: t- instead of z-statistics
Date   Thu, 21 Jul 2011 23:49:40 -0500

At 10:27 PM 7/21/2011, John Luke Gallup wrote:
The coefficient test statistics reported after most estimation models are z-statistics because we only know their asymptotic distribution (even if we assume that the errors are normally distributed). Only with simple linear models, like OLS, where the coefficients are linear functions of the y's, and only when we assume the errors are normally distributed, do the coefficient test statistics have a known small sample distribution - a t-distribution. Note that a t-statistic is equal to a z-statistic asymptotically.

Since the VEC is not a linear estimator, it does not report t-statistics.

Please join in if you see any problems with what I said.

Potential gap/flaw in that reasoning? When data are svyset, we get t-statistics rather than z-stats, e.g.

webuse nhanes2f
svy: logit diabetes age black female

I'm not sure what the moral of that is, but Stata does report t statistics in many more situations than just after OLS.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index