R square statistics problem
in [Matlab]
|
From: Kiril on 16 May 2010 05:45 Hello folks, I'm need a little help about static toolbox. I have project to make, a regression analysis and i use "regress" - [B,BINT,R,RINT,STATS] = REGRESS(Y,X). I'm interesting in vat STAT, it returns R2 - stat, F - stat , variance err and so on. But i can't find how Matlab computes R2 - stat and F - stat and so on. I have answers on the project and there are little error about R2 - stat for example (err about 0.005)... So, can some one explain how is computed vector STATS from REGRESS? Thanks!
From: us on 16 May 2010 05:55 "Kiril " <kkirqkov(a)gmail.com> wrote in message <hsoerf$m3n$1(a)fred.mathworks.com>... > Hello folks, > I'm need a little help about static toolbox. I have project to make, a regression analysis and i use "regress" - [B,BINT,R,RINT,STATS] = REGRESS(Y,X). > I'm interesting in vat STAT, it returns R2 - stat, F - stat , variance err and so on. > But i can't find how Matlab computes R2 - stat and F - stat and so on. > I have answers on the project and there are little error about R2 - stat for example (err about 0.005)... So, can some one explain how is computed vector STATS from REGRESS? > Thanks! one of the solutions edit regress; % jump to line #139 (ver 2007b)... us
|
Pages: 1 Prev: Variable name for a table in matlab? Next: 3d reconstruction |