Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: missing t statistics


From   Ronan Conroy <[email protected]>
To   [email protected]
Subject   Re: st: missing t statistics
Date   Fri, 19 Oct 2007 10:10:40 +0100

This looks like very strange data indeed - those standard errors are minute. dividing the coefficient by its standard error is going to result in a number of the sort studied by the late Professor Hubert Mungus - a humungus quantity.

Have a look at your data - maybe the explanation lies there.

On 19 Oct 2007, at 02:20, Yun Liu wrote:


Hi, Stata users,

I am running median regressions. Sometimes stata reports estimated
coefficients, standard errors and confidence intervals, but the t
statistics turn out to be missing. Could someone please tell me what
this means? Thank you! Below is an example:

qreg chgcomp swf swm swmcdftenure swfcdf* i.ind

Median regression Number of obs = 528
Raw sum of deviations 2.22e+07 (about 6806.4399)
Min sum of deviations 1.74e+07 Pseudo R2 = 0.2164

---------------------------------------------------------------------- --------
chgcomp | Coef. Std. Err. t P>|t| [95% Conf. Interval]
------------- +----------------------------------------------------------------
swf | 44.91122 .0000596 . 0.000 44.91111 44.91134
swm | -1.589599 4.38e-06 . 0.000 -1.589608 -1.589591


P    Before printing, think about the environment
=================================
Ronan Conroy
[email protected]
Royal College of Surgeons in Ireland
Epidemiology Department,
120 St Stephen's Green, Dublin 2, Ireland
+353 (0)1 402 2431
+353 (0)87 799 97 95
http://www.flickr.com/photos/ronanconroy/sets/72157601895416740/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index