Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: New version of -parmest- on SSC

From   Roger Newson <>
Subject   st: New version of -parmest- on SSC
Date   Tue, 20 Aug 2002 21:33:00 +0100

Dear All

Thanks to Kit Baum, there is now a new version of the -parmest- package downloadable from SSC. The -parmest- package saves the results of an estimation command as a Stata data set with 1 observation per parameter, or 1 observation per parameter per by-group, and data on estimates, confidence limits, P-values, and other results if requested. Type -ssc describe parmest- in Web-aware Stata to find out more.

The new version fixes a bug, which caused -parmest- to fail if used with the survey estimation commands -svymean-, -svyratio- and -svytotal- when these commands were specified with the -available- option instead of the -complete- option. -parmest- now works with these survey estimation commands when the -available- option is specified. In these circumstances, -parmest- now calculates confidence limits and P-values using estimates in e(est) and variances extracted from e(V_db), and the default degrees of freedom formula used is e(N_psu)-e(N_strata), as specified in -[R] svymean- under the sub-section "Confidence intervals". All other Stata estimation commands store the estimates in e(b), the variances in e(V) and the degrees of freedom in e(df_r), and so do -svymean-, -svyratio- and -svytotal- when the -complete- option is specified instead of the -available- option. When working with these commands, -parmest- calculates confidence intervals and P-values from e(b), e(V) and e(df_r), as before.

I would like to thank Dan Blanchette of the University of North Carolina for informing me about the bug and for helping me towards a solution, and Jeff Pitblado of Stata Corporation for explaining to us (via Statalist) the exceptional behaviour of -svymean-, -svyratio- and -svytotal- when the -available- option is specified, and for reassuring me that no other Stata command behaves in this way.

Best wishes

Roger Newson

Roger Newson
Lecturer in Medical Statistics
Department of Public Health Sciences
King's College London
5th Floor, Capital House
42 Weston Street
London SE1 3QD
United Kingdom

Tel: 020 7848 6648 International +44 20 7848 6648
Fax: 020 7848 6620 International +44 20 7848 6620
or 020 7848 6605 International +44 20 7848 6605

Opinions expressed are those of the author, not the institution.

* For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index