I'm am completely aware that all the other terms need to be calculated in order to determine whether the value is significant. I even mentioned this in 482056.

And, I guess I could be misusing your code, but when I feed it these values 5 0 4 1, it produces the same output exactly as my "misguided" code. Funnily enough, for those values, it produces the same output as tmoertel's (apparently equally misguided) code.

Is it only when given the larger set of test values 989 9400 43300 2400 that your special code does something extraordinarily clever that I'm to stupid to understand?

$T->start( '[5 0 1 4]' );
print Fishers_Exact::fishers_exact( 5, 0, 1, 4 );
$T->stop( '[5 0 1 4]'  );
$T->report;

$T->start( '[989 9400 43300 2400]' );
print Fishers_Exact::fishers_exact( 989, 9400, 43300, 2400 );
$T->stop( '[989 9400 43300 2400]' );
$T->report;

__END__
P:\test>FET-tlm.pl
0.02380952380952380952380952380
  1 trial  of [5 0 1 4] (    917us total), 917us/trial

0.9999999999999999999999999999999999999999999999999999999999999999999
999999999999999999999999999999999999999999999999999999999999999999999
999999999999999999999999999999999999999999999999999999999999999999999
999999999999999999999999999999999999999999999999999999999999999999999
999999999999999999999999999999999999999999999999999999999999999999999
999999999999999999999999999999999999999999999999999999999999999999999
999999999999999999999999999999999999999999999999999999999999999999999
99999999999999999999999999999999952665545273822897512768877675
  1 trial  of             [5 0 1 4] (    917us total), 917us/trial

  1 trial  of [989 9400 43300 2400] (   1.353s total), 1.353s/trial
[download]