In: Statistics and Probability
14-E1. Below are some (fictitious) correlations between all pairs of three variables. The means and standard deviations are also give. Imagine that they were obtained from a sample of 35 randomly chosen individuals.
Income |
Education |
Age |
|
Income ($1000) |
1.0 |
0.43 |
0.22 |
Education (years) |
0.43 |
1.00 |
-0.58 |
Age (years) |
0.22 |
-0.58 |
1.00 |
Mean |
45.2 |
11.3 |
47 |
Stdev |
8.5 |
3 |
12 |
b. Here we need to test the significance of
correlation coefficients at
level of significance, i.e. we need to test
against,
at
level of significance.
So this is a both tailed size
test.
The test statistic for this test is
where
is correlation coefficient and
is the sample size.
We know
.
Assuming
, for the given value
,the critical value for this test is
.
So we conclude that a correlation coefficient is
significant if ,
, i.e. we reject the
hypothesis
.
a. (i) Now for the correlation
coefficient between Education and Income is
.
Hence this is significantly different from zero.
(ii) For the correlation coefficient between
Age and Education is
.
Hence this is not significantly different from zero.
(iii) For the correlation coefficient between
Age and Income is
.
Hence this is not significantly different from zero.
c. A infinitely large sample will be required.
d. If the age units are changed to months mean and standard deviation of all the variables will be 12 times of the current values but the vales of correlation coefficients will not be changed.