Thanks, Anthony! It worked!! Only, for future reference, I had to exclude INCOME from the reset (which is the variable in the svymean function) q50 <- update( q50 , AGECL = factor( AGECL ) , RACECL = factor( RACECL ) )
2017-07-09 15:52 GMT-04:00 Anthony Damico <ajdam...@gmail.com>: > try resetting your factor levels and re-run? > > q50 <- update( q50 , INCOME = factor( INCOME ) , AGECL = factor( AGECL ) , > RACECL = factor( RACECL ) ) > > > > > On Sun, Jul 9, 2017 at 2:59 PM, Orsola Costantini via R-help < > r-help@r-project.org> wrote: > >> Hi all, >> >> When I try the following with pkg Survey it returns the error below: >> >> ftable(svyby(~INCOME, ~AGECL+RACECL, svymean, design=q50), >> rownames=list(AGECL=c("<35", "35-44", "45-54", "55-64", >> "65-74", ">=75"), >> RACECL=c("white non hispanic", "non white or hispanic")) >> >> Error in rbind(matrix("", nrow = length(xcv), ncol = length(xrv)), >> charQuote(makeNames(xrv)), : >> number of columns of matrices must match (see arg 3) >> >> When I do the follwing instead all is good. But it only works for small >> subsets! >> >> h<-svymean(~interaction(INCOME, AGECL, RACECL), q3) >> >> fh<-ftable(h, rownames=list(AGECL=c("<35", "35-44", "45-54", "55-64", >> "65-74", ">=75"), >> RACECL=c("white non his", "non white or hispanic"))) >> >> >> any idea why? >> >> Thanks!!! >> >> U. >> >> [[alternative HTML version deleted]] >> >> ______________________________________________ >> 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/posti >> ng-guide.html >> and provide commented, minimal, self-contained, reproducible code. >> > > [[alternative HTML version deleted]] ______________________________________________ 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.