Statalist


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

st: istdtize


From   Javier Sanchez <jsanchez@upei.ca>
To   statalist@hsphsun2.harvard.edu
Subject   st: istdtize
Date   Mon, 21 Sep 2009 14:03:38 -0300

I was trying to use the istdize command and realized that some of the outputs (eg. Number of observed events) are incorrect and change each time I run the command (this problem was posted before but could not find an answer). Also the number of cases might be different from the same strata when looking at the stratified outputs as compared to the summary outputs. After exploring the ado file, I found that there might be a couple of lines missing in the file. The basic problem is when there is more than one group, the total number of cases is no added and the command is using a random line with the cases from that particular observation. Since I am not an expert on Stata, I added this basic lines to the ado file and the outputs look correct but it would be nice if somebody else could look into this as well since there are many papers citing the use of this command that might have some errors.

istdize.ado
line 1 ............
.
.
line 163 qui by `Gc': replace `topop'=`topop'[_N]
**************NEW*****************
       qui by `Gc': replace `cases'=sum(`cases')
       qui by `Gc': replace `cases'=`cases'[_N]
************** END NEW************



--
Javier Sanchez, DVM, PhD
Research Chair Risk Analysis
Atlantic Veterinary College
550 Univ. Ave
Charlottetown
C1A 4P3, PE
Canada

tel +1 902.566.0803
fax +1 902.566.0823

*
*   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   |   What's new   |   Site index