[R] transpose rows and columns for large data

John Dougherty jwd at surewest.net
Thu Dec 1 00:01:58 CET 2016

On Tue, 29 Nov 2016 17:22:47 +0000 (UTC)
Elham - via R-help <r-help at r-project.org> wrote:

> Is there another way (I prefer a way with Excel)?

Search on "friends don't let friends use excel for statistics."
Spreadsheets are an inherently perilous way to do statistics and Excel
specifically is notoriously poor. In fact the reason I originally began
using dedicated statistical packages (STATA first and now R) is that
spreadsheets (Excel in my case) can throw subtle errors that can create
problems. immediately, or even worse - later.  I had Excel return a
negative variance. Since variance is a squared value, unless you are
dealing with some very exotic numbers including imaginary values, a
negative variance is an absurd result.  Further investigation revealed
that other stat routines provided with Excel at the time were also
throwing errors that could look reasonable and thus be missed.  It was
also simply using erroneously constructed methods and providing
outright wrong results to things like Chi-square calculations.  



More information about the R-help mailing list