Welch's t-test: Difference between revisions
m
→Using Burkhardt's 'incomplete beta': oops, stray variable, add comment marker
SqrtNegInf (talk | contribs) (→Using Burkhardt's 'incomplete beta': general trimming and clean-up) |
SqrtNegInf (talk | contribs) m (→Using Burkhardt's 'incomplete beta': oops, stray variable, add comment marker) |
||
Line 995:
$variance1 = $variance1/(@$array1-1);
$variance2 = $variance2/(@$array2-1);
my $Welch_t_statistic = ($mean1-$mean2)/sqrt($variance1/@$
my $DoF = (($variance1/@$array1+$variance2/@$array2)**2) /
(
Line 1,006:
# from here, translation of John Burkhardt's C code
my $beta = lgamma($A) + 0.57236494292470009 - lgamma($A+0.5); # constant is
my $eps = 10**-15;
my($ai,$cx,$indx,$ns,$pp,$psq,$qq,$qq_ai,$rx,$term,$xx);
| |||