search for: marascuilo

Dear list, I have very little experience in dealing with proportions, i am sure this is a very simple question but i could find no suitable answer beyond doing a chi-sq test and then using the Marascuilo procedure as a post-hoc analysis. I am simply wanting to know if the proportions ( i.e the number of Yes / No) significantly differ between the cases and if so which cases are significantly high or low? proportion <- structure(list(Case = structure(1:11, .Label = c("A", "B&quot...

...ed case, like here: after before + - + 10 14 - 5 53 So usually i use the mcnemar.test(stats). Due to mortality, I now got the problem that my sample sizes in both factors are not equal any more -- there are less cases in the "after" condition. I already learned that Ekbohm (1982) and Marascuilo adressed the problem conceptually, but I'm not that good at writing my own functions. Can anyone give me a hint what function/test/package in R to use? Thank you very much for your help, Christian -- Christian Montel Eligo GmbH - B??ro Berlin Friedrichstr. 90 D - 10 117 Berlin Fon (030) - 2...