Re: Fisher's Exact Test and Chi-square


iandjmsmith@xxxxxxx wrote:
harriscsuiucedu@xxxxxxxxx wrote:
I have a number of questions about these two...
....
- FET takes a long time to compute if n is large (in comparison to
chi-square). Are there approximation algorithms of FET directly (that
is attempts to approximate the sum of hypergeometric values)?

Just a couple of comments on computing 2-sided FET for the 2x2 case
when the entries in the table are large.

As you have hinted, the computation is just the sum of the
probabilities of the tails of the hypergeometric distribution. So you
need a function to evaluate the cdf of the hypergeometric distribution
quickly and accurately.

In http://members.aol.com/iandjmsmith/Accuracy.htm there are notes on
how to do this.

Nice. Any references for where these came from (and other
possibilities)? Abramowitz and Stegun?

Mitch

.

Relevant Pages

  • Re: Fishers Exact Test and Chi-square
    ... Are there approximation algorithms of FET directly (that ... Just a couple of comments on computing 2-sided FET for the 2x2 case ... the computation is just the sum of the ... probabilities of the tails of the hypergeometric distribution. ...
    (sci.stat.consult)
  • Re: CPUs, thread pools, and wasted time.
    ... should be actively running wasteTime() and my CPU utilization should be ... A single CPU ... sum += Math.cos;} ... Try computing some eigenvalues or solving simple ordinary differential equations to REALLY waste time. ...
    (comp.lang.java.programmer)
  • Re: ASSIGNMENT
    ... third, and fifth (i.e., alternating) prime numbers. ... but fortunately I redid the sum. ... low-order bit of t to select every other prime. ... ends up computing 2*5*11, which is the result we were looking for. ...
    (comp.lang.c)
  • Re: standard deviation, but without the mean
    ... There's a standard formula for computing the variance from a running ... Suppose Xsum is the sum of the the first n numbes and that X2 is ... Just keep track if X2 and Xsum as you go. ... Actually this is not a correct algorithm, ...
    (sci.stat.math)
  • Re: Sum of Gaussian functions
    ... I'm not James but permit me to answer. ... by uniqueness of Fourier coefficients. ... James's sum agrees to ... which are periodic or doubly periodic by computing sum Fwhere ...
    (sci.math.num-analysis)