Fisher Exact test value is not presented in the Spss output as the Chi square value .I need to tabulate this value in my net result tables. I can easily detect the Chi value but not Fisher Exact. any help ?
Dear Alyaa,
use these:
http://www.socscistatistics.com/tests/fisher/Default2.aspx
https://www.graphpad.com/quickcalcs/contingency1.cfm
Hello Alyaa. If your row & column totals are not fixed in advance, then I would recommend using the N-1 Chi-square rather than Fisher's exact test (aka, the Fisher-Irwin test). Ian Campbell has done a very nice simulation study on this (published in Statistics in Medicine). Campbell's simulations show that the N-1 Chi-square performs well provided all expected frequencies are 1 or higher.
For SPSS users, by the way, the "Linear-by-linear association" test result from CROSSTABS (on a 2x2 table) is equivalent to the N-1 Chi-square. See the links below for more information.
HTH.
https://sites.google.com/a/lakeheadu.ca/bweaver/Home/statistics/notes/chisqr_assumptions
http://www.iancampbell.co.uk/twobytwo/background.htm
http://onlinelibrary.wiley.com/doi/10.1002/sim.6808/full
It occurs to me now that Alyaa may be asking why the Value column in the SPSS output (see example linked below) is empty for Fisher's exact test. The answer is that there is no test statistic corresponding to the Chi-square values shown on the other rows of that table. With the Fisher-Irwin test (aka., Fisher's exact test), all you get is a probability value. HTH.
http://www.ats.ucla.edu/stat/spss/whatstat/choose9.gif
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS