In article <[EMAIL PROTECTED]>,
Thom Baguley <[EMAIL PROTECTED]> wrote:
>Karl L. Wuensch wrote:
>> misunderstanding of the logic of hypothesis testing. Sigh. Maybe Frank
>> Schmidt is correct when he suggests that we abandon tests of significance
>> (Schmidt, F. L. (1996). Statistical significance testing and cumulative
>> knowledge in psychology: Implications for training of researchers.
>> Psychological Methods, 1, 115-129.), because the typical researcher just is
>> not capable of understanding the logic of hypothesis testing -- but I
>I wish it were that easy. Students and researchers also have misconceptions
>about supposed alternatives to significance tests (CIs, power, meta-analysis).
>IMO the misconceptions are less common only to the extent that the alternatives
>are less widely taught.
The real alternative is decision theory. One needs to consider
the totality of consequences in the totality of possible relevant
states of nature, and choose an action to balance these.
So for hypothesis testing, one needs to balance the two errors.
For confidence intervals, one needs to balance the error probability
against the decreased utility of larger intervals.
--
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 and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
