on 1/31/01 12:48 PM, [EMAIL PROTECTED] wrote: > On 1/27/01, 9:15:22 AM, [EMAIL PROTECTED] wrote regarding Re: statistics: > > >> Does anyone have any Metatalk statistical functions to determine >> 1.correlation coefficients(Pearson and/or Spearman), >> 2.multiple and logistic regression? >> mike > > Pearson's, Spearman's, Point Biserials, and contingency correlation > coefficients aren't too hard. Multiple regression will require someone > with a working knowledge of matrix algebra on a lot of time on his or her > hands, but it is doable within MetaTalk, though ou may be better off > saving data in text format, then importing it into SPSS or SAS. If > anyone is interested, I'll contribute my 2 cents. Pearson's, Spearman's, Point Biserials, and the contingency coefficient (for 2x2 tables) are all the same statistic: applying the standard Pearson cross-products formula to the data in each case will produce *exactly* the same result as would the special-case (computational convenience) formulae. Matrix algebra is not necessary, and for purposes such as stepwise multiple linear regression will actually get in the way. I have a little treatise I wrote on stepwise multiple linear regression in meta/hypercard, including the relevant meta/hypertalk code. An example mc stack containing it all may be downloaded from: http://home.uleth.ca/~vokey/software/regression.sit: -- "The sun oozed over the horizon, shoved aside darkness, crept along the greensward, and, with sickly fingers, pushed through the castle window, revealing the pillaged princess, hand at throat, crown asunder, gaping in frenzied horror at the sated, sodden amphibian lying beside her, disbelieving the magnitude of the frog's deception, screaming madly, "You lied!" -- Winner of the Bulwer Lytton Contest, wherein one writes only the first line of a bad novel. John R. Vokey, Ph.D. Chair Department of Psychology and Neuroscience University of Lethbridge Archives: http://www.mail-archive.com/metacard@lists.runrev.com/ Info: http://www.xworlds.com/metacard/mailinglist.htm Please send bug reports to <[EMAIL PROTECTED]>, not this list.
