Can you provide a sample data set (i.e., matrix) that you consider to be "large"? Also, could you give me an idea of how long it takes to compute Pcutoff without using arithmetic optimizations? (I would like to try out a quick Haskell-based implementation I whipped up on a real data set.)
| [reply] |
(44,289! 11,800!) (10,389! 45,700!)
-----------------------------------
56,089! 989! 9,400! 43,300! 11,800! 2,400!
Which infinite precision will calculate, but it will be quite slow. And remember, in order to determine if the result is significant, there are 11,000 more of these calculations to perform and these numbers are still relatively small. And, theoretically at least, the FET can be applied to more than a 2x2 matrix.
Examine what is said, not who speaks -- Silence betokens consent -- Love the truth but pardon error.
Lingua non convalesco, consenesco et abolesco. -- Rule 1 has a caveat! -- Who broke the cabal?
"Science is about questioning the status quo. Questioning authority".
The "good enough" maybe good enough for the now, and perfection maybe unobtainable, but that should not preclude us from striving for perfection, when time, circumstance or desire allow.
| [reply]
[d/l] |
For this matrix, I can compute the exact Pcutoff in about 1 second (on a 1.6-GHz Celeron laptop). How long does the brute-force approach take?
[thor@arinmir fishers-exact-test]$ cat ex1.dat
989 9400
43300 2400
[thor@arinmir fishers-exact-test]$ time ./fet < ex1.dat > /dev/null
real 0m1.007s
user 0m0.991s
sys 0m0.012s
| [reply]
[d/l] |
Quick question: If the sample size is so large, is there a reason you aren't using the Chi-square test? My understanding is Fisher's Exact Test may be preferred when the sample size isn't large enough to reasonably support the large-sample approximation for the Chi-square test. Since you have a large sample, why not take the easy road?
| [reply] |
| [reply] |
BrowserUk,
Once you have a division math problem of factorials that has been reduced by some factoring method (GCD or prime), it can be reduced even further by substraction.
47! * 1091!
-----------
55! * 1001!
(1002 .. 1091)
--------------
(48 .. 55)
This is only a savings when the factorial is being calculated by multiplying all the terms and not by some other approximation method.
| [reply]
[d/l] |
The original problem, framed in terms of arrays, is to reduce a fraction.
The
equation above is less general.
The less general problem can be restated as reduce a fraction where the numerator and denominator are both the product of factorials.
An example of the original problem is to reduce
(9 * 8 * 8 * 8 * 6 * 4 )/(5 * 3 * 2)
An example of the factorial problem is to reduce
(9! * 8! * 8! * 8! * 6! * 4! )/(5! * 3! * 2!)
Do I understand correctly, are you are interested in the factorial type of problem?
| [reply] |
( 9 * 8 * 7 * 6 * 5 * 4 * 3 * 2
* 8 * 7 * 6 * 5 * 4 * 3 * 2
* 8 * 7 * 6 * 5 * 4 * 3 * 2
* 8 * 7 * 6 * 5 * 4 * 3 * 2
* 6 * 5 * 4 * 3 * 2
* 4 * 3 * 2 )
/
( 5 * 4 * 3 * 2
* 3 * 2
* 2)
And it reduces to
( 3 * 4 * 7 * 6 * 5 * 4 * 3 * 2
* 4 * 7 * 6 * 5 * 4 * 3 * 2
* 4 * 7 * 6 * 5 * 4 * 3 * 2
* 2 * 7 * 6 * 5 * 4 * 3 * 2
* 3 * 4 * 3 * 2
* 4 * 3 * 2 )
/
( 1 )
Which eliminates factorials completely (and, in this case the need for division). More importantly and relevantly, it reduces the magnitude of the intermediate terms. In the FET, the scale of this reduction should be considerably more significant than in this example.
Examine what is said, not who speaks -- Silence betokens consent -- Love the truth but pardon error.
Lingua non convalesco, consenesco et abolesco. -- Rule 1 has a caveat! -- Who broke the cabal?
"Science is about questioning the status quo. Questioning authority".
The "good enough" maybe good enough for the now, and perfection maybe unobtainable, but that should not preclude us from striving for perfection, when time, circumstance or desire allow.
| [reply]
[d/l]
[select] |
