Voices of dissent: statistical hypothesis testing
Kenneth Collins
k.p.collins at worldnet.att.net
Sat Nov 9 04:59:40 EST 2002
Basically, I agree with the gist of the position Glen 'outlined'
below, but I come at the problem from a different perspective.
In the work I've done, I've explored deeply into how this or that
'scientific' bandwagon's being jumped-on is the primary thing that
determines the course that 'science' will take - has nothing to do
with Science, and everything to do with groupwise coersed-consensus.
Apply Statistics to such, and the =only= thing that can happen is
that the 'statistics' will positively or negatively reflect =only=
with respect to that which is bounded within groupwise
coersed-consensus, which amounts to just more, meaningless, groupwise
coersed-consensus, not Science.
That it's so is really-Big-Time-Sorrowful stuff, 'cause there are
problems whose Resolutions actually matter.
k. p. collins
Glen M. Sizemore wrote in message <3dcc1e88_1 at news.teranews.com>...
>From the following website:
>
>http://www.arts.auckland.ac.nz/edu/staff/jhattie/StatSignif.html
>
>
>
>"If we can control statistical significance simply by changing
sample size,
>if statistical significance is not equivalent to scientific
significance, if
>statistical significant testing corrupts the scientific method, and
if it
>has only questionable relevance to one out of fifteen threats to
research
>validity, then I believe we should eliminate statistical
significance
>testing in our research. Such testing is not only useless, it is
also
>harmful because it is interpreted to mean something it is not"
(Carver,
>1978, p. 392).
>
>· "The test of statistical significance in psychological research
may be
>taken as an instance of a kind of essential mindlessness in the
conduct of
>research" (Morrison & Henkel, 1970, p. 436)
>
>· "Significance tests do not provide the information that scientists
need,
>and furthermore, they are not the most effective method for
analyzing and
>summarizing data" (Clark, 1963, pp. 469).
>
>· "The time has arrived for educational researchers to divest
themselves of
>the yoke of statistical hypothesis testing" (Shulman, 1970, p. 389).
>
>· "The time has arrived to exorcise the null hypothesis" (Cronbach,
1975, p.
>124).
>
>· A null hypothesis test is a ritualized exercise of devil's
advocacy
>(Abelson, 1995, p. 12).
>
>· "It would hardly be exaggeration to describe hypothesis testing as
a
>method of giving a misleading answer to a question which nobody is
asking!"
>(Novick & Jackson, 1974, p. 245).
>
>Carver, R.P. (1978). The case against statistical significance.
Harvard
>Educational Review, 48, 378-399.
>
>Morrison, D.E., & Henkel, R.E. (1970). Significance tests in
behavioral
>research: Skeptical conclusions and beyond. In D.E. Morrison & R.E.
Henkel
>(Eds.), The significance testing controversy: A reader. Chicago:
Aldine.
>
>Clark, C.A. (1963). Hypothesis testing in relation to statistical
>methodology. Review of Educational Research, 33, 455-473.
>
>Shulman, L.S. (1970). Reconstruction of educational research. Review
of
>Educational Research, 40, 371-393. Task Force on Statistical
Inference
>Initial report.
>
>Cronbach, L.J. (1975). Beyond the two disciplines of scientific
psychology.
>American Psychologist, 30, 116-127.
>
>Abelson, R.P. (1995) Statistics as principled argument. Hillsdale,
NJ:
>Erlbaum.
>
>Novick, M., & Jackson, P. (1974). Statistical Methods for
Educational and
>Psychological Research New York: McGraw Hill.
>
>
>
>
>
>
>
>
>
More information about the Neur-sci
mailing list