Determine whether the sample provides enough evidence to conclude that there is a significant, nonzero correlation in the population. In each case, use a two-tailed test with ?=0.50.
a. A sample of n = 18 with r = -0.50
Work done:
the formula for the "test statistic" is:
(r*sqrt{n-2}) / sqrt{1-r^2}
where 'sqrt' is 'the square root of', 'r' is the correlation, and r^2 is 'r squared'
So for the first one, the test statistic is (-.5 * sqrt{16}) / sqrt{1-.25} = -2 / sqrt{.75} = 2.309
Not sure what my answer means in regards to if there is a significant, nonzero correlation or not.
Please help. Thanks.
a. A sample of n = 18 with r = -0.50
Work done:
the formula for the "test statistic" is:
(r*sqrt{n-2}) / sqrt{1-r^2}
where 'sqrt' is 'the square root of', 'r' is the correlation, and r^2 is 'r squared'
So for the first one, the test statistic is (-.5 * sqrt{16}) / sqrt{1-.25} = -2 / sqrt{.75} = 2.309
Not sure what my answer means in regards to if there is a significant, nonzero correlation or not.
Please help. Thanks.