Dear Statalisters,
I sent a private message to the author of 'swboot', and a copy to the list
in case that she has changed her email address...
I just downloaded 'swboot' (versions 2.2.0 - 13 Aug 2000) to use with a
small dataset (2 groups of 15 subjects) and several sets of predictors
(personality traits).
Here is the output I get with the first set of predictors:
. swboot SAMPLE_T0 fi di tas es bs dis, rep(100)
Model: Stepwise Logistic Regression
Outcome: -- SAMPLE_T0
Options: pr=.1 pe=.05 n=30
invalid '9'
r(198);
Setting trace on, I located the line on which the error occured:
- disp _n(1) in gre "Options: pr=" in yel "`pr'" in green " pe=" in yel
"`pe'" in green " n=" in yel "`sample'"
Options: pr=.1 pe=.05 n=30
- disp " "
- }
- if `n'>_N {
disp in red "There are only " in yel _N in red " available " "observations
for this model;"
}
- while `numreps'<=`reps' {
- quietly save `tempds', replace
invalid '9'
bsample `sample'
if "`regtype'"=="lin" {
I'm grateful for any help you can provide me with.
Yours sincerely,
Herv�.
--
Herv� CACI, MD, PhD
Child and Adolescent Psychiatry
Service de P�diatrie
H�pital de l'Archet 2
151, route de Saint Antoine de Ginesti�re
06202 Nice Cedex 3 -- FRANCE
Tel: 04 92 03 60 74
Fax: 04 92 03 60 81
email: [email protected] (at work)
[email protected] (at home)
Web: http://perso.wanadoo.fr/herve.caci
*
* 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/
