natural response rate in probit

[Albert Moore]

Hi

I was wondering if there was a way to adjust for the natural response rate, or background rate, when using probit regression in Stata.

Example- in the study of mortality in insects exposed to various doses of a toxin, there may be a baseline rate of mortality in insects that were not exposed to the toxin at all. In SPSS and SAS there are options that adjust the probit regression based on this baseline rate.

Is there a way to adjust for this in Stata?

Thank you

[Carlo Lazzaro]

Albert:
welcome to the list.
As far as I know, a similar option (-exposure()) is available for -poisson- in Stata.

[Albert Moore]

Hi

Thanks so much for the reply and the welcome! I am not sure if my data would fit a poisson distribution. I'll look at it and see.

take care

[Richard Williams]

probit has an offset option. In poisson, specifying exposure(x) is the same as specifying offset(lnx). So maybe you want something like that for Probit. But having said that, I suspect not.

Perhaps the docs for SPSS and SAS will make it clearer what needs to be done. If in doubt on what to do, I would try to take some result I got from SPSS or SAS and see if I can replicate it in Stata.

[Richard Williams]

Here is the online documentation I could find for SAS and SPSS on natural response rates:

https://support.sas.com/documentatio...it_sect005.htm

https://www.ibm.com/support/knowledg...p/idh_5440.htm

Maybe if you dig further through the docs you can find out the actual mathematical calculation that is done.

[Maarten Buis]

I made an error, I would need more time than I have to write down the correct likelihood.