In conjunction with the other comments that have already been made on this
topic, I'd simply note that testing the left tail of a chi-square
distribution in the case of a goodness-of-fit test is equivalent to testing
whether the fit is "better" than expected. This was the basis a few years
ago of the assertion that the results of Mendel's original genetic crosses
were "too" good, and that he must have fudged the data to correspond more
closely to his conceptual model of particulate genes and alleles (the basis
of modern Mendelian genetics).
Rich Strauss
At 07:26 PM 2/5/01 +0900, you wrote:
>hi, all.
>
>Isn't a chi-squre test inherently a 'one-sided sig. test'?
>
>I just read a paper claiming that it uses a 'one-sided' rather than
>'two-sided' test. So it regards a chi-square value of 3.3 (df=1) is
>significant at the level of 0.05. (As you all know, the critical value
>of chi-square (df=1) at the alpha of 0.05 is 3.84.)
>
>I know this claim is simply errorneous. But I am just wondering
>whether there can be any occasion one may use 'two-sided' test
>with the chi-square distribution.
>
>Any comment will be a great help.
>
>Thanks in advance.
>
>June
========================
Dr Richard E Strauss
Biological Sciences
Texas Tech University
Lubbock TX 79409-3131
Email: [EMAIL PROTECTED] (formerly [EMAIL PROTECTED])
Phone: 806-742-2719
Fax: 806-742-2963
========================
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
