I am trying to fit a GLM model using R (version 0.64.1 Win95) onto a dataframe(dtse) consisting of 3348 rows with 4 variables: - 3 factors: (c)31 levels, (m)12 levels (s)9 levels) - 1 integer: (n) The data consists of counts and is strongly overdispersed. I try fit the following model dtse.glm<- glm(n~s+c+m, data=dtse, family=quasi(link=log, variance=mu)) When I issue this command R sometimes answers, but sometimes (using the same dataset) simply crashes without any error message in the R-console. Only the standard Win95 error-dialog appears. Can anybody advise me how to overcome (workaround) this problem. Cor Berrevoets National Institute for Coastal and Marine Management POBOX 8039 4330 EA Middelburg Netherlands -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._