==================================================================
The gateway between this list and the sci.stat.edu newsgroup will
be disabled on June 9.  This list will be discontinued on June 21.
Subscribe to the new list EDSTAT-L at Penn State using the web
interface at http://lists.psu.edu/archives/edstat-l.html.
==================================================================
.
Suppose there is one factor with two levels. I could either run one-way
ANOVA or unpaired t test. I always thought that the unpaired t-test would be
the same as one-way ANOVA in the following sense: the F test in ANOVA for
two factor level means being equal (or factor effect) would be equivalent to
the unpaired t test for the difference betwen the two factor level means
since F = t^2 holds in this case.

After I took a close look of the formulas, I now realize that unpaired t
test is exactly equivalent to a one-way ANOVA when the latter is used to
test for a difference in means between two factor levels. Then I have
problem understanding the subtle difference: It seems that it is possible to
have significant factor effect while there is no significant difference
between the two factor level means. My question is: How is this possible?

Thanks,
Gang Chen

Reply via email to