2.1
Tukey:
diff
lwr
upr
p adj
21
0.18
0.76981435 0.4098143
0.8185430
31
0.38
0.20981435 0.9698143 0.2903038
41
0.44
0.14981435
1.0298143
0.1844794
32
0.56
0.02981435
1.1498143
0.0657945
42
0.62
0.03018565
1.2098143
0.0376691
43
0.06
0.52981435
0.6498143
0.9910783
Bonferroni method has same mean but different range, with range width 1.24.
The Tukey method gives shorter intervals.
2.2
a)
The Tukey critical value for
α
= .01 is 3.67.
The Bonferroni critical value
is 3.77.
from Table 2.4, we see that no contrast test statistic exceeds either
value.
b)
We would expect at least one contrast to be statistically significantly
different at the .05 level since we rejected the F test null hypothesis at the .05
level.
However, this methodology gives us no information about comparisons
at the .01 level.
c)
Since the pvalue for the F test is .02, we would not expect any contrast to
be significantly different at the .01 level.
2.3
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '11
 PETERQIAN
 Statistics, Normal Distribution, Regression Analysis, Null hypothesis, Statistical hypothesis testing, Errors and residuals in statistics

Click to edit the document details