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 on April 23, and its replacement, statalist.org is already up and running.


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

st: RE: RE: xtfevd


From   Murat Genc <murat.genc@otago.ac.nz>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: RE: xtfevd
Date   Thu, 16 Feb 2012 11:29:59 +0000

Thank you very much Nick.  I wasn't aware of the protocol about explaining where I got the program from.  I obtained it from Thomas Plumper's web pages, http://www.polsci.org/pluemper/ssc.html

Your observation about the method is spot on, and you were indeed very polite.  I nevertheless wanted to produce results by using the method and make comparisons.  I can get it work with a different data set and a model.  So, your comment 4) suggests that this particular problem is related to the memory available on my computer.

Thanks again.

Murat


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nick Cox
Sent: Thursday, 16 February 2012 11:57 p.m.
To: 'statalist@hsphsun2.harvard.edu'
Subject: st: RE: xtfevd

-xtfevd- is a user-written program. It is not even found by -findit-. Either way, you are asked to explain where user-written programs you refer to come from. I don't think the authors of -xtfevd- are members of Statalist, so I doubt that you will get good support on it through Statalist. 

Incidentally, a Google for fixed effects vector decomposition will yield references to discussion papers maintaining that this method has been oversold, to put it fairly politely. I can't adjudicate on this -- I've not even read the papers -- but my impression is that the critics are weightier authorities than the proponents. (I are aware from argument from authority is often regarded as a fallacy, but it's what I have here.)

That aside, Mata can't find a way to allocate a matrix that is [6168, 6168]. Deeper diagnosis of that problem may depend on some combination of (1) the details of -xtfevd- (2) the details of your dataset and what this command implies (3) the memory available on your computer (4) the flavour of your Stata. 

Nick 
n.j.cox@durham.ac.uk 

Murat Genc

I am getting the following error message when I try to do an estimation by using xtfevd.  I've never seen this message before, so I don't know what to do.  Can anyone suggest something?

The error message I get is:

. xtfevd  lrealexp  lmig  ldist    lgdpcons_o  lgdpcons_d comlang_off contig  colony  com
> lang_ethno  gatt_d  rta  comcur  lmigmpc  lmigeec  lmigasea, invariant( ldist colony co
> mlang_ethno comlang_off contig)
                       *:  3900  unable to allocate real <tmp>[6168,6168]
                vc_eta():     -  function returned error
                 <istmt>:     -  function returned error
r(3900);
 

*
*   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/

*
*   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