Rick Froman wrote: > > > That is so cool. Would it be safe to say that Fisher, since this was > basically the genesis of this concept, was here using the word > "significance" in the usual sense and only later did it come to take > on the specialized meaning of "a statistical result that is not likely > to be due to chance"? > First of all, I should that I am no specialist in early statistics (though it is a side-interest of mine), so I may be wrong. However, I think that Fisher is, here, inventing the concept of statistical significance before your eyes. He is using the common term, "significant,"in a particular technical way for (perhaps) the first time. It is not that he didn't recognize the technical construction he was putting on the term, but that he was "sharpening up" what the term should mean in a statistical context.
By the way, in the quotation, he is talking about the normal distribution in particular. Regards, Chris -- Christopher D. Green Department of Psychology York University Toronto, ON M3J 1P3 Canada 416-736-2100 ex. 66164 [EMAIL PROTECTED] http://www.yorku.ca/christo/ "Part of respecting another person is taking the time to criticise his or her views." - Melissa Lane, in a /Guardian/ obituary for philosopher Peter Lipton ================================= > *From:* Christopher D. Green [mailto:[EMAIL PROTECTED] > > "The rapidity with which the probability falls off as the deviation > increases is well shown in these tables. A deviation exceeding the > standard deviation occurs about once in three trials. Twice the > standard deviation is exceeded only about once in 22 trials, thrice > the standard deviation only once in 370 trials, while Table II. shows > that to exceed the standard deviation sixfold would need nearly a > thousand million trials. The value for which P =ยจ.05, or 1 in 20, is > 1.96 or nearly 2 ; it is convenient to take this point as a limit in > judging whether a deviation is to be considered significant or not. > Deviations exceeding twice the standard deviation are thus formally > regarded as significant. Using this criterion, we should be led to > follow up a negative result only once in 22 trials, even if the > statistics are the only guide available. Small effects would still > escape notice if the data were insufficiently numerous to bring them > out, hut no lowering of the standard of significance would meet this > difficulty." > > *Fisher, Ronald A.* (1925). /Statistical methods for research workers/ > <http://psychclassics.yorku.ca/Fisher/Methods/>. Originally published > in London by Oliver and Boyd. (pp. 46-47). > > And how about single-case studies? > > > What about them? > > Regards, > Chris > > -- > > Christopher D. Green > Department of Psychology > York University > Toronto, ON M3J 1P3 > Canada > > > > 416-736-2100 ex. 66164 > [EMAIL PROTECTED] <mailto:[EMAIL PROTECTED]> > http://www.yorku.ca/christo/ > > > > > > "Part of respecting another person is taking the time to criticise his > or her views." > > - Melissa Lane, in a /Guardian/ obituary for philosopher Peter Lipton > > ================================= > > > --- To make changes to your subscription contact: Bill Southerly ([EMAIL PROTECTED])
