Everyone is welcome here --- except those who have borrowed books from me for and have not returned them yet!

F and MinF' computations

Posted on August 25, 2000 in stats

Given by subjects and by items F values, this program computes MinF' (see Herbert H. Clark (1973) The Language-as-fixed-Effect Fallacy: A critique of Language Statistics in Psychological Research in Journal of Verbal Learning and Verbal Behavior, 12, 335-359.).

There would be an applet here if your browser supported java. Notes:

  1. Press ENTER (or Ctrl-ENTER) to move from one cell to the next (or to the previous).

  2. It is possible to enter only one F value to compute its associated probability.

3.. A bug was corrected on Nov 17, 2005: the computed p-value was wrong when the F-value was less than 0.5. Hopefully, it is now correct. (thanks to Arnout Koornneef and Timothy Desmet for pointing out the bug). This should not have created problems given that F<0.5 is quite far from the usual significance threshold...

  1. I am not advocating the use of MinF' !!! (I wrote this applet many years ago to train myself in Java). It may be better to use a mixed effect model approach considering both subject and items as random factors (See, e.g., Baayen, R.H., Statistics in Psycholinguistics: A critique of some current gold standards. In Mental Lexicon Working Papers 1, Edmonton, 1-45)