In article <[EMAIL PROTECTED]>, Jerry Dallal <[EMAIL PROTECTED]> wrote: >Herman Rubin wrote:
>> In article <[EMAIL PROTECTED]>, >> Jerry Dallal <[EMAIL PROTECTED]> wrote: >> >Herman Rubin wrote: >> >> If you, and your students, want to understand statistics, >> >> do not start them out with ANY statistical procedures >> >> until they understand probability (NOT how to calculate >> >> probabilities) as well as evaluation of consequences and >> >> probability modeling. >> >For some unknown reason, today it struck me that if students >> >*really* understood probability, there would be a period not >> >survived by many that would begin with their asking, "Well, then, >> >why go on?" >> In a sense you can say that this is correct; if someone in >> another field understands probability, probability modeling, >> and the evaluation of consequences, a properly formulated >> problem needs nothing more than calculation, assuming that >> it is known how to calculate for that problem. >In truth, I was seeing the cup as half-empty rather than half-full. >My concern was that seeing how approximate probability models often >are, one might be tempted to abandon statistical methods entirely! Whatever is taught about statistical procedures should be done using the idea of robustness, or only such things as binomial or hypergeometric situations can be handled reasonably. This might not be a bad idea in any case. but it means that precise levels of tests and precise confidence intervals cannot usually be obtained. From a decision point of view, this is not too important, as being near the "optimum" point is not much worse than being there. -- This address is for information only. I do not claim that these views are those of the Statistics Department or of Purdue University. Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399 [EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
