In: Statistics and Probability
#34
Big Rock Insurance Company did a study of per capita income and volume of insurance sales in eight Midwest cities. The volume of sales in each city was ranked, with 1 being the largest volume. The per capita income was rounded to the nearest thousand dollars.
Reading | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
Rank of insurance sales volume | 6 | 8 | 4 | 1 | 3 | 2 | 5 | 7 |
Per capita income in $1000 | 16 | 13 | 17 | 19 | 18 | 15 | 12 | 14 |
Using a 0.01 level of significance, test the claim that there is a monotone relation (either way) between rank of sales volume and rank of per capita income.
(a) Using a rank of 1 for the highest per capita income, make a table of ranks to be used for a Spearman rank correlation test.
City | Rank of insurance sales volume x |
Rank of per capita income in $1000 y |
d = x - y | d2 |
1 2 3 4 5 6 7 8 |
Σd2 = |
(c) Compute the sample test statistic. (Use 3 decimal
places.)
a)
x-y= | |||
x rank | y rank | d | d2 |
3 | 4 | -1 | 1 |
1 | 7 | -6 | 36 |
5 | 3 | 2 | 4 |
8 | 1 | 7 | 49 |
6 | 2 | 4 | 16 |
7 | 5 | 2 | 4 |
4 | 8 | -4 | 16 |
2 | 6 | -4 | 16 |
∑d2 | 142 |
b)
level of significance =0.01
null hypothesis: | ps | = | 0 | |
Alternate Hypothesis: | ps | ≠ | 0 |
c)
test statistic = | rs=1-6Σd2/(n(n2-1))= | -0.690 |
d) 0.05 < p value <0.10
e) fail to reject the null,,,,data are not statistically significant