There probably is a better way to do this but I'd suggest getting an overall total and then splitting the data.frame into it's 3 component parts then apply the equations below to get the sums and the number of missing values for each subject over all four data.frames. ================================================= apply(dd, 1, sum, na.rm=TRUE)# sum of responses
count.NAS=function(x) length(which(is.na(x))) #from J. Valbuena apply(dd,1,count.NAS) # number of NA's per subject ================================== Then prorate for each of the four data.frames. I hope this makes sense. --- Bob Green <[EMAIL PROTECTED]> wrote: > Hello, > > I am hoping for some advice as to how I can prorate > a number of scale > items that comprise a score. At least 69 of 159 > cases have at least 1 > value missing (65 cases have H7 missing). The > maximum number of missing is > 5. > > I want to compute a total score, a score for the H > items, the R items and > C items. > > H1, H2, H3, H4, H5, H6, H7, H8, H9, H10, C1, C2, C3, > C4, C5, R1, R2, R3, > R4, R5 > > I am uncertain as to whether a series of IF > statements are required or > some other strategy. Prorating is the method a > researcher using this scale > has recommended. > > Any advice is appreciated, > > Bob Green > > ______________________________________________ > 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. > [[replacing trailing spam]] ______________________________________________ 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.
