> Run that function hourly with plyr > > output.hourly <- dlply(df.i1,"tshour",cor.dat) Why not output.hourly <- ddply(df.i1,"tshour",cor.dat) ? Generally you want to work with data frames in R, if at all possible. Hadley -- Assistant Professor / Dobelman Family Junior Chair Department of Statistics / Rice University http://had.co.nz/