Hi, i was working with this model > mq<-glm(rojos~edadysexo*zona*estacion,quasipoisson)
and i get this minimal adequate model > anova(mq5,test="F") Df Deviance Resid. Df Resid. Dev F Pr(>F) NULL 518 64799 edadysexo 2 1556.5 516 63243 8.9434 0.0001524 *** zona 4 13590.6 512 49652 39.0448 < 2.2e-16 *** estacion 1 10069.1 511 39583 115.7112 < 2.2e-16 *** zona:estacion 4 2879.6 507 36704 8.2728 1.809e-06 *** I know the correct syntaxis to make a post-hoc comparisonfor single factor > summary(glht(mq5, linfct=mcp(edadysexo="Tukey"))) Estimate Std. Error z value Pr(>|z|) M - H == 0 0.28976 0.09541 3.037 0.0060 ** SUB - H == 0 -0.22610 0.22626 -0.999 0.5609 SUB - M == 0 -0.51586 0.21921 -2.353 0.0441 * (Adjusted p values reported -- single-step method) and with a single factor involved in an interaction > summary(glht(mq5, linfct=mcp(estacion="Tukey", interaction_average=TRUE))) Estimate Std. Error z value Pr(>|z|) verano - primavera == 0 -1.352 0.151 -8.952 <2e-16 *** (Adjusted p values reported -- single-step method) But how can i test the interaction "zona:estacion", I've tried to do this ways, but doesn't work 1. > summary(glht(mq5, linfct=mcp((estacion:zona)="Tukey", interaction_average=TRUE))) 2.> s<-interaction(zona,estacion) > mqs<-glm(rojos~edadysexo+zona+estacion+s,quasipoisson) > summary(glht(mqs, linfct=mcp(s="Tukey"))) Error en modelparm.default(model, ...) : dimensions of coefficients and covariance matrix don't match Anyone can helps? ----- Mario Garrido Escudero PhD student Dpto. de Biología Animal, Ecología, Parasitología, Edafología y Qca. Agrícola Universidad de Salamanca -- View this message in context: http://r.789695.n4.nabble.com/glht-multicomparisons-with-an-interaction-factor-tp4288343p4288343.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ 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.