Dear all, I'm doing univariate Poisson regressions using the "glm" and "glm.fit" functions. I have 5 independent datasets and each dataset, has one response variable and more than 20 factors to test. Currently, I run one regression at a time and manually take notes of the results in excel to have a quick overview on what is going on in my data. My poor method is very time-consuming and I was looking for a faster and more reliable way to do all the regressions. I'm quite sure that R could do all of this for me but I can't think of a way to tell it...
What I want R to do is 1) running one regression at a time in a particular dataset. 2) saving results. Here, I'm interested in AIC, Beta coefficient of the factor, the z value and the p value of the factor 3) formatting results in a table with column names as follow: factor; beta coefficient; z value; p value; aic 4) exporting the table in a way that I could read it in excel. In that way, I would repeat the operation for each of the 5 datasets rather than for the 100 regressions. I hope you could help me with this. Thanks a lot for your answers. Jérôme Lemaître Ph.D. student Dpt biologie Université Laval Québec, Canada ______________________________________________ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html