[R] results from t-test

Robert W. Baer, Ph.D. rbaer at atsu.edu
Sat May 1 20:54:26 CEST 2004


 >All the numeric output looks OK, but the statement that the alternative
> >hypothesis is accepted seems rather strange.
>
> I think you misread it.  It says alternative hypothesis: true mean is not
equal to 0
> which should be read as  alternative hypothesis: "true mean is not equal
to 0"
> not
> alternative hypothesis: true,  mean is not equal to 0
>
> Duncan Murdoch
>
Interestingly, I had a student fooled by a similar re-statement of the
alternative hypothesis in R output (although I don't think it was the
t-test) just last week.  At the time, I wondered
1)  Why the null AND the alternative weren't stated (guessed the answer was
parsimony)
2)  Why if only one was stated, the convention was to re-state the
alternative rather than the null hypothesis.
ans
3)  Since technically the hypothesis is made a priori, why is it not
re-iterated until AFTER producing the test results on the output.

I think it is this last logic that my student and Patrick.  Shouldn't the
hypothesis re-statement preceed the output?

Rob Baer




More information about the R-help mailing list