Russel-Research-Method-in-Anthropology

Bivariate Analysis: Testing Relations 597
TABLE 20.2
Descriptive Statistics for Data in Table 20.1
CW-USA
CW-Liberia
N of cases 43 41
Minimum 0 2
Maximum 6 12
Mean 2.047 4.951
95% CI Upper 2.476 5.705
95% CI Lower 1.617 4.198
Standard Error 0.213 0.373
Standard Deviation 1.396 2.387
s 2 (431)1.3962 (411)2.387 2
43412
Now we can solve for t:
81.85227.91
82
t 2.0474.951
3.778(.0477) 2.904
.180 2.904
.4243 6.844
3.778
Testing the Value of t
We can evaluate the statistical significance of t using appendix C. Recall
from chapter 19 that we need to calculate the degrees of freedom and decide
whether we want a one- or a two-tailed test to find the critical region for rejecting
the null hypothesis. For a two-sample t-test, the degrees of freedom equals:
(n 1 n 2 )2
so there are 43 41 2 82 degrees of freedom in this particular problem.
If you test the possibility that one mean will be higher than another, then
you need a one-tailed test. After all, you’re only asking whether the mean is
likely to fall in one tail of the t-distribution (see figure 7.7). With a one-tailed
test, a finding of no difference (the null hypothesis) is equivalent to finding
that you predicted the wrong mean to be the one that was higher. If you want
to test only whether the two means are different (and not that one will be
higher than the other), then you need a two-tailed test. Notice in appendix C
that scores significant at the .10 level for a two-tailed test are significant at the
.05 level for a one-tailed test; scores significant at the .05 level for a two-tailed
test are significant at the .025 level for a one-tailed test, and so on.
We’ll use a two-tailed test for the problem here because we are only inter-