----- Original Message ----- From: [EMAIL PROTECTED] (Herman Rubin) Date: Saturday, April 24, 2004 4:39 pm Subject: Re: [edstat] Why do we transform data????
> In article <[EMAIL PROTECTED]>, > Robert J. MacG. Dawson <[EMAIL PROTECTED]> wrote: > > >> >Herman Rubin wrote: > > >> >> This is not done that often, and is generally quite difficult. > >> >> It requires changing the form of the model. The more typical > >> >> transformations attempt to get normal marginals, and there is > >> >> rarely justification for this. It has done harm; many of the > >> >> newer IQ tests never return "profoundly gifted", as this is > >> >> beyond the range which the "normal" transformation of the scores > >> >> from the too-small sample yields. > > >I responded: > > >> > This may not be a bad thing, as it is not clear that > the tests are > >> >designed to make accurate distinctions for that part of the > range of > >> >intellectual ability. > > >to which Herman Rubin responded: > > >> There is no way now > >> that a gifted child can get anything like an appropriate > >> education in the public schools, and failing to recognize > >> giftedness, or its extent, is really criminal. > > >If the public school system had any interest in recognizing (and > >giving an appropriate education to) highly gifted children it > could > >do so without IQ tests. If it doesn't, we cannot blame the tests. > > This is true, but this will not be done unless forced. > If the child's IQ score is not enough to get into Mensa, > the school can improperly claim that the child does not > need more than the schools are now providing. If the > IQ test reported 160 instead, more pressure could be > made. > Better IQ tests will not force the issue. There needs to be some basic changes in attitude. Too many folks take the phrase "all men are created equal" to the extreme in expecting that everyone should be precisely equal after schooling. Any plan to provide services to the bright students is met with resistance both inside and outside the schools. It is quickly labled "elitist" and therefore evil. Even programs that are shown to improve performance among the low end students are labled elitist if they increase the spread between high and low. It is sad that in the name of "equality" bright students are held back. But until there is a change in attitude and legal requirements it won't matter if a student is gifted or merely bright. They will be ignored. > > If the maximum score attainable is (say) interpreted as > >an IQ of 140, and if that score is only attainable by somebody > who > >ought to be offered an enriched program, then that can be used > >to make this decision. Scaling differently so that a perfect mark > >was intepreted as 180 or as 90 out of 90 would not add any more > >information. > > As I have said elsewhere, enrichment is a total waste of > time and resources. Even the "ordinary" students should > get much more, but this would make the curriculum too > difficult for a fair-sized portion of the students; this > seems to be the case already. At least 20% of the students > should enter college in their early teens with the equivalent > of the current "honors" high school program. I would agree that much more should be available to all students. That would be wonderful. Each and every child should be educated to the maximum allowed by their ability. But right now that would be considered too elitist by too many. Sad, really. I do not see how enrichment is a waste of time or resources. If brighter students are better educated they should be able to accomplish more as adults. > > > > In short - schools that are prepared to admit to the > >existence of gifted children had better learn to recognize > >then by more valid criteria than IQ tests. > > -Robert Dawson > > The easiest way to get this started is to disestablish the > public schools, and to make alternatives affordable. Many public school teachers in my community started at the prochial school. I doubt very much that their ability level changed going from one school to the next. What does change is the demands made of them. In private school parents have an expectation that teachers will demand high levels of performance. In public school legislators, vocal parents, and many in the public expect that teachers will keep all kids at the same level. Until these expectations change it won't matter if education is public or private. Parents who demand high performance will get kids who do as well as their ability allows. Parents who don't care will get children who don't do as well as they should. > Also, > requiring teachers to understand subject matter as determined > by subject matter scholars, not educatists, who would not be > required or expected to pass the majority of the current > teachers or applicants. I tend to agree. I would like to see more subject matter material and few education courses. Fortunately in South Dakota the secondary ed math teacher is required to take the equivilant of a math major less one course. Unfortunately the el ed major is required only to take college algebra and two semester of math for el ed majors. Michael > -- > 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, Department of Statistics, Purdue University > [EMAIL PROTECTED] Phone: (765)494-6054 FAX: > (765)494-0558 > . > . >**************************************************** Michael Granaas [EMAIL PROTECTED] Assoc. Prof. Phone: 605 677 5295 Dept. of Psychology FAX: 605 677 3195 University of South Dakota 414 E. Clark St. Vermillion, SD 57069 ***************************************************** = . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
