topic Re: regression model when the dependent variable is count in Statistical Procedures

regression model when the dependent variable is count

mydamj — Thu, 01 Aug 2024 08:46:26 GMT

when the dependent variable is count (output of proc freq) and most of the independent variables are also count, what regression model is ideal to use. Also, what SAS procedure should be used?

example: Instead of individual data, grouped data(like county wise) data is available.

Re: regression model when the dependent variable is count

sbxkoenk — Thu, 01 Aug 2024 15:42:15 GMT

Art or science? Choosing the right regression model
By Udo Sglavo on October 11, 2021
https://blogs.sas.com/content/subconsciousmusings/2021/10/11/art-or-science-choosing-the-right-regression-model/
Which regression technique is appropriate for my data?
By Udo Sglavo on October 5, 2021
https://blogs.sas.com/content/subconsciousmusings/2021/10/05/which-regression-technique-is-appropriate-for-my-data/
SAS Global Forum 2008 -- Paper 371-2008
Count Data Models in SAS®
WenSui Liu & Jimmy Cela , ChoicePoint Precision Marketing, Alpharetta, GA
https://support.sas.com/resources/papers/proceedings/pdfs/sgf2008/371-2008.pdf
Sample 59236: Fitting Zero-Inflated Count Data Models by Using PROC GENMOD
https://support.sas.com/kb/59/236.html
Or look at PROC COUNTREG or PROC CNTSELECT.

BR, Koen

Re: regression model when the dependent variable is count

StatDave — Thu, 01 Aug 2024 17:03:00 GMT

If, at the subject level, the response is binary (such as yes/no, positive/negative) so that your data are aggregated binary data and you have the numerator and denominator counts making up the proportions, then you can fit a logistic model in procedures such as LOGISTIC, PROBIT, GENMOD, GAM, ADAPTIVEREG and others by using the events/trials syntax in the MODEL statement. The model assumes that the proportions represent a set of independent Bernoulli trials and have a binomial distribution. See the example in the Getting Started section of the PROC LOGISTIC documentation. But if your data are counts of some event over a period of time (such as person-years) such that the ratio of count/time is a rate that can exceed 1, then you would typically model the rate using a Poisson or negative binomial model with the log of the time variable as an offset. See the Poisson Regression example in the Getting Started section of the PROC GENMOD documentation.