[R] mc nemar test

[Peter Dalgaard]

"David Hajage" <dhajage at gmail.com> writes:

> Hello R users,
> 
> I would like to perform a mc nemar test.
> There is my data :
> __________________________________
> x <- matrix(4:1,2,2)
> 
> x
> 
>      [,1] [,2]
> [1,]    4    2
> [2,]    3    1
> __________________________________
> 
> My population is too small for normal approximation.
> __________________________________
> library(concord)
> 
> mcnemar.mh(x)
> 
> $statistic
> [1] 0.2
> 
> $p
> [1] 0.6547208
> 
> Warning message:
> low cell counts - consider binomial test in: mcnemar.mh(x)
> 
> ___________________________________
> 
> Do you have an advice to perform this test ? Is there a non-parametric one ?
> Thank you very much.

The advice would seem to be rather precise: 

> binom.test(2,5)

        Exact binomial test

data:  2 and 5
number of successes = 2, number of trials = 5, p-value = 1
alternative hypothesis: true probability of success is not equal to 0.5
95 percent confidence interval:
 0.05274495 0.85336720
sample estimates:
probability of success
                   0.4


-- 
   O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
  c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
 (*) \(*) -- University of Copenhagen   Denmark          Ph:  (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)                  FAX: (+45) 35327907