Dear Miluji, I went through different combinations, and find it elegant to sum the values with respect to ID + High/Low Date levels like if this was a list of Dose/Material/Group experiments:
x[x$Date %in% c(4143, 4147),"j"] <- tapply(x$Value, paste0(x$ID, ifelse(x$Date>4143, 2, 1)), sum) This way, you escape the «every 4th observation» criterium, IMHO instead «using» the dataframe in contrast to creating new information or interpreting the structure of the data frame ... I'm sorry if this only creates confusion and a «what is he talking about?!» awkwardness by not answering the question in a precise way ... Best, Rasmus ______________________________________________ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.