[R] chi square exact test

David L Carlson dcarlson at tamu.edu
Wed Mar 6 22:20:03 CET 2013


Actually, the http://www.sussex.ac.uk/its/pdfs/SPSS_Exact_Tests_20.pdf file indicates that for small samples and a one-way chi square test, SPSS uses a multinomial distribution to tabulate the distribution of chi square for a given N, K, and probability of membership in each group. In package stats, the dmultinom() function can be used to accomplish this. The last example on the help page shows the steps. 

----------------------------------------------
David L Carlson
Associate Professor of Anthropology
Texas A&M University
College Station, TX 77843-4352


> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Milan Bouchet-Valat
> Sent: Wednesday, March 06, 2013 1:17 PM
> To: Knut Krueger
> Cc: r-help at stat.math.ethz.ch
> Subject: Re: [R] chi square exact test
> 
> Le mercredi 06 mars 2013 à 18:38 +0100, Knut Krueger a écrit :
> > Am 06.03.2013 18:29, schrieb Milan Bouchet-Valat:
> > > Le mercredi 06 mars 2013 à 18:03 +0100, Knut Krueger a écrit :
> > >> Am 06.03.2013 14:27, schrieb Nicole Ford:
> > >> Dear Nicole,
> > >> my be you are wondering about, but I know Google an I am using
> google
> > >> before I am asking here.
> > >>
> > >> If you are more familiar with googl,e please help me to find the
> search
> > >> term where I can find
> > >> the R function for
> > >> chi square exact usable for one column test for a sample size less
> than 6
> > >>
> > >> You are welcome to use this search:
> > >>
> > >> http://www.giyf.com/chi%20square%20exact
> > >>
> > >>
> > >> Thanks in advane Knut
> > > See ?fisher.test.
> > fisher test needs two columns I need  a one column exact test
> > |x|
> >
> > either a two-dimensional contingency table in matrix form, or a
> factor
> > object.
> >
> > |y|
> >
> > a factor object; ignored if |x| is a matrix.
> Sorry, I missed that part. Can you tell us more about the test you do
> in
> SPSS? Are you testing the adequacy of a given distribution to the data?
> In short: what do you test?
> 
> Is that test documented somewhere? I found this document, but there
> does
> not seem to be such a test there:
> http://www.sussex.ac.uk/its/pdfs/SPSS_Exact_Tests_20.pdf
> 
> 
> Regards
> 
> >
> > Knut
> >
> > 	[[alternative HTML version deleted]]
> >
> > ______________________________________________
> > R-help at 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.
> 
> ______________________________________________
> R-help at 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.



More information about the R-help mailing list