Thanks a lot!!!
On Mon, Mar 4, 2013 at 12:46 PM, MacQueen, Don <macque...@llnl.gov> wrote: > What Jim said separately is correct, and I would suggest following his > advice. > But there are some points worth looking at in your method. > > See this example: > > > item1 <- item2 <- item3 <- item4 <- 1:4 > > > > matrix1<-cbind(item1, item2, item3, item4) > > > > z <- c(TRUE,TRUE,FALSE,TRUE) > > > > matrix2 <- cbind(item1[z], item2[z], item3[z], item4[z]) > > > > matrix3 <- cbind(item1=item1[z], item2=item2[z], > + item3=item3[z], item4=item4[z]) > > > > print(matrix1) > item1 item2 item3 item4 > [1,] 1 1 1 1 > [2,] 2 2 2 2 > [3,] 3 3 3 3 > [4,] 4 4 4 4 > > > > print(matrix2) > [,1] [,2] [,3] [,4] > [1,] 1 1 1 1 > [2,] 2 2 2 2 > [3,] 4 4 4 4 > > > > print(matrix3) > item1 item2 item3 item4 > [1,] 1 1 1 1 > [2,] 2 2 2 2 > [3,] 4 4 4 4 > > Points to consider: > > Since your "z" is a vector of logical values, you don't need > item1[z==T] > instead, use > item1[z] > > Your column names on matrix2 do not look correct, given how you created > matrix2. > > Not that you can specify column names when you create the matrix using > cbind, as in my matrix3 example. > > -Don > > > -- > Don MacQueen > > Lawrence Livermore National Laboratory > 7000 East Ave., L-627 > Livermore, CA 94550 > 925-423-1062 > > > > > > On 2/28/13 5:53 PM, "Pablo Menese" <pmen...@gmail.com> wrote: > > I'm performing item response theory with eRm packages > I am excluding the persons that doesn't fit in the infit/outfit persons. > for that I created a condition. then I have to create a new subset or > matrix but with the condition. > > So: > > ORIGINAL > > matrix<-cbind(item1, item2, item3, item4) > > IF I PERFORM A head(matrix) > > item1 item2 item3 item4 > 3 2 3 1 > 3 1 2 4 > > THEN I CREATE THE LOGIC CONDITION > > z<-thing==T > > THEN I TRY TO CREATE THE NEW MATRIX BUT WITH THE CONDITION > > matrix2<-cbind(item1[z==T], item2[z==T], item3[z==T], item4[z==T]) > > THE ISSUE IS THAT IF I PERFORM A head(matrix2) > > I1 I2 I3 I4 > 3 2 3 1 > 3 1 2 4 > > The names of the columns change at all. > > CAN ANYONE HELP ME TO KEEP THE SAME NAMES? > > [[alternative HTML version deleted]] > > ______________________________________________ > 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. > > [[alternative HTML version deleted]] ______________________________________________ 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.
