Dear R-List, is it possible to calculate a three-factor (two factors with 9 levels and one with three) analysis of variance with repeated (or replicates, sorry, don?t know the correct word) measurements in R? My dataframe looks like fx fy fz iv 1 1 1 56 1 1 2 45 [...] 9 9 3 50 this six times where fx and fy (9 levels), fz (3 levels) are factors, iv is the independent variable. However, there are only 123 different factor combinations for the 3 factors. I?ve got six measurements in the dataframe for every factor combination. I?ve read that it?s nessecary to setup the dataframe that all columns contain the value of iv for a combination of the three factors at different levels, and each row reflects the observed responses. So my dataframe should have 123 columns and 6 rows. It?s very easy to make a dataframe with 123 colums and 6 rows from the existing data, but how can I conserve the factor information, so every column specifies a combination of the three factors and the rows reflect the repeated observations? Maybe the dataframe should look like fx1-fy1-fz1 fx1-fy1-fz2 .... fx9-fy9-fz3 1. observe 56 45 50 ... And how do I calculate the anova? Or is there another possibility? Many thanks, Sven -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- 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 _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._