Hi, I would like to calculate a Conway-Maxwell-Poisson<http://artax.karlin.mff.cuni.cz/r-help/library/compoisson/html/00Index.html> Regression with the cmp function of the COMPoissonReg package. However, when I try to run the model, ... cmp_model = cmp(formula = Vergleich ~c_0001 * Art_Vergleich ,data=Mindset_AV_long_sel) ...I get an error, although I get the output as well: #(Intercept) c_00012 Art_Vergleich2 c_00012:Art_Vergleich2 0.5978370 -0.3881165 -0.4567584 0.8161324 Error in xmat %*% par[1:length(betainit)] : requires numeric/complex matrix/vector arguments I tried to continue with the output I got, but at some point in the procedure suggested by Seller and Lotze, I get another error and no further output:
Error in xmat %*% betahat : requires numeric/complex matrix/vector arguments Is it, maybe, because my two predictors are dichotomous and not continuous? Or is it just a stupid mistake somewhere I should be embarrassed about? Is there any other way to calculate a regression with the COM poisson distribution? That might be the quicker solution. I appreciate your help! And sorry, if the post is redundant and/or stupid - this is my first post. Best, Silke [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.