[[stuff removed]]
>>
>> Gary.McClelland@Colorado.edu
>> Psycholgy, Univ of Colorado
>>
>
>These are very important points.
>
>There are a number of statistical things
>that have outlived their utility. A master, such as Fisher, can
>stamp a methodology so firmly into the minds of his followers that
>it becomes almost impossible to replace it when it becomes obsolescent.
>
>The advent of the computer and widely used statistical packages is
>having the same effect that the advent of printing had on language --
>the freezing of methods of expression. I can think of advantages
>for language, but off the top of my head I cannot think of any for
>statistics.
>
>It is difficult to write a commercial computer program that departs
>from materials that appear in the standard textbooks. If one does,
>reviewers are sure to denigrate the program, and readers of the reviews
>will look elsewhere. I believe Paul Velleman observed someplace on this
>thread or another that there were better ways than stepwise regression
>to deal with the problem, and that his Data Desk offers an alternative.
>I think his observations were not given due weight.
>
>In my case, experimental design for engineers, the standard textbooks
>present a considerable problem. They are structured for statisticians,
>and many of the methodologies depend on a world view alien to
>engineers. Fortunately statistics is rich enough that one can choose
>paths less well traveled -- criticism for not employing standard methodologies
>
>is to be expected.
>
>
> Bob Wheeler, ECHIP, Inc.
I'd like to extend and redirect this thread a bit because it's a real
concern of mine.
We in applied disciplines (that is, where _statistics_ is applied, not that
our research necessarily is applied) have a serious problem when it comes
to new methods. There are at least two sources of pressure to not
change--colleagues and "the market." I know that
Gary.McClelland@Colorado.edu, the author of the first quote above, has
experienced them, as have I. Many of us who teach statistics in disciplines
like psychology actually know that our discipline misuses statistics
terribly sometimes, and we may actually try to teach what we know to be
better ways. But then the students, and most especially our colleagues who
deal with our students, complain that they're not learning "the old way."
We have have an obligation to produce students who can read the existing
literature in the discipline, and who can communicate with our colleagues
who don't know the "better ways."
Bob Wheeler (just above) complained about the standard textbooks. Well, why
are they that way? Simple--in most cases it's what the market wants. I've
just finished checking the final page proof for my second statistics text
for psychologists. This book, and my first, represents a compromise between
what I know to be the "better way" for many things, and editor/reviewer
judgments of "what will sell." In both cases, my compromise has produced
books that are labeled as "high level" for an undergraduate course, and
therefore have a more limited market. And that translates into less revenue
for the publisher (and for me, not coincidentally). And in fact if the book
is pitched too high, the publisher may even stand to lose money, and I will
have lost several years of my life on a project with little compensation.
This is a real problem, and I see no easy way out. Gary McClelland and
Charles Judd, and their publisher, took a considerable risk when they
brought out a statistics book for psychologists that focusses entirely on
statistical modeling. It's not exactly news to most of us that that
approach is the "current" and the "correct" way to proceed. But they are
the pioneers. And also more adventurous than my publisher wanted to be.
(Maybe there's hope--there are at least 2 or 3 similar books out for
psychology students now built around the same theme.)
Does anyone think they have a way out of this problem? Does anyone share my
concern and interest in finding a way around this colleague/market dilemma?
Dick Lehman
--------------------------------------------------------------------------
Richard S. Lehman R_Lehman@ACAD.FANDM.EDU
Department of Psychology
Franklin & Marshall College Voice (717)291-4202
PO Box 3003 FAX (717)291-4387
Lancaster, PA 17604-3003
"I'd rather be blowing glass."