Re: st: nl: missing standar error

[Maarten Buis <maartenlbuis@gmail.com>]

--- Jay wrote:
>> It sounds to me like the variance of that parameter is essentially 0
>> or some other violation of the requirement that a covariance matrix be
>> positive definite. Try outputting the covariance matrix of the
>> parameter estimates and see if there are other missing parts or if
>> (when looked at in correlation scale) the correlation between one
>> parameter and another is very high.

--- Christina asked:
> What do you mean by "outputting the covariance matrix of the
> parameter estimates"?

type after you finished the -nl- command:
matlist e(V)

and look at the matrix in the way Jay suggested.

--- Jay wrote:
>> You may have an empirically unidentified parameter.

--- Christina asked:
> Could you please give me a hint how to identify the problem? I

In that case there is nothing you can do. To quote John Tukey (1986,
p.74-75): "The combination of some data and an aching desire for an
answer does not ensure that a reasonable answer can be extracted from
a given body of data."

Hope this helps,
Maarten

John Tukey (1986), "Sunset salvo". The American Statistician 40(1):72-76.

---------------------------------
Maarten L. Buis
WZB
Reichpietschufer 50
10785 Berlin
Germany

http://www.maartenbuis.nl
---------------------------------
*
*   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/