Re: Fisher's Exact Test / Freeman-Halton-Test

Posted by David Marso on Jun 02, 2012; 3:16pm
URL: http://spssx-discussion.165.s1.nabble.com/Fisher-s-Exact-Test-Freeman-Halton-Test-tp5713482p5713489.html

Maybe you are running it incorrectly?
*PLEASE* post your syntax in the future.  
It is difficult to try to guess what you are fumbling around with.
Not even your other stats are correct from that table of counts.
-------------------------------------------------------------
My results using the following syntax:
data list free / x y w.
begin data
1 1 3 1 2 1 1 3 3 2 1 0 2 2 3 2 3 7
end data.
weight by w.
CROSSTABS/TABLES=y BY x /STATISTIC=CHISQ/METHOD=EXACT TIMER(5).

Chi-Square Tests
  Value df Asymp. Sig. (2-sided) Exact Sig. (2-sided) Exact Sig. (1-sided) Point Probability
Pearson Chi-Square 5.234 2 .073 .072
Likelihood Ratio 6.319 2 .042 .072
Fisher's Exact Test 4.609 .072
Linear-by-Linear Association 3.191 1 .074 .119 .070 .052
N of Valid Cases 17
a 5 cells (83.3%) have expected count less than 5. The minimum expected count is 1.24.
b The standardized statistic is 1.786.

drfg2008 wrote

I always thought, SPSS would compute "Fisher's Exact Test" equivalant to the Freeman-Halton-Test. But this doesn't seem to be so.

Following data example:

line A B Sum
1 3 0 3
2 1 3 4
3 3 7 10
Sum 7 10 17


SPSS result: p=0,152

-------------------------------------------------
Chi-Square Tests
        Value df Asymp. Sig. (2-sided) Exact Sig. (2-sided) Exact Sig. (1-sided) Point Probability
Pearson Chi-Square 4.635a 2 .099 .152
Likelihood Ratio 5.783 2 .055 .152
Fisher's Exact Test 4.194 .152
Linear-by-Linear Association 3.602b 1 .058 .070 .055 .043
N of Valid Cases 18
a 5 cells (83.3%) have expected count less than 5. The minimum expected count is 1.33.
b The standardized statistic is 1.898.
-------------------------------------------------

But the Freeman-Halton p-Value should be p(A) = p(B) = 0.07229535170711625
according to:

-> http://vassarstats.net/fisher2x3.html