I found out my mistake just now and it was due to my sampling
procedure, which made my results not perfectly reproducible. So I get
different results every time I ran it anyway, regardless of the coding
of the missing values.
Thank you very much, Maarten, for giving it a try and suggesting me to
use the missing option. I did end up using it.
Lian
On 1/7/06, Maarten buis <[email protected]> wrote:
> Hi Lian,
>
> From your post I assume that your likelihood function consists two parts, one that uses a
> varialble ts1 if y==1 and another (ts2?) when y~=1. If y~=1 than ts1 has no meaningful values, and
> if you used "." without the "missing" option the sample size got "screwed up". So you replaced
> them with either 2 or 9999999. My guess is that the problem is the very large number 9999999. Are
> the results from the model with the missing option and the model with missing at 2 close to each
> other, while the 99999999 model is not?
>
> HTH,
> Maarten
>
> -----------------------------------------
> Maarten L. Buis
> Department of Social Research Methodology
> Vrije Universiteit Amsterdam
> Boelelaan 1081
> 1081 HV Amsterdam
> The Netherlands
>
> visiting adress:
> Buitenveldertselaan 3 (Metropolitan), room Z214
>
> +31 20 5986715
>
> http://home.fsw.vu.nl/m.buis/
> -----------------------------------------
>
> Lian Jian wrote
> > What troubles me is that when I did not know the existence of
> > this "missing" option, I recoded the missing values from "."
> > to 999999999 using "recode ts1 miss=999999999", thinking that
> > it wouldn't matter. Theoretically, it shouldn't matter because
> > ts1 is only used when y == 1. When y == 0, the value of ts1
> > does not enter the likelihood function. I have made sure
> > whenever y==1, ts1 has a valid value. And whenever y==0, ts1
> > is missing. What troubles me is that when the missing values
> > of ts1 are coded as 2 or 999999999, it gives me different
> > estimation results.
>
>
>
> ___________________________________________________________
> To help you stay safe and secure online, we've developed the all new Yahoo! Security Centre. http://uk.security.yahoo.com
> *
> * 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/
>
--
Lian Jian
*
* 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/
