For a sample of 20 New England cities, a sociologist studies the crime rate in each city (crimes per 100,000 residents) as a function of its poverty rate (in %) and its median income (in $1,000s). A portion of the regression results is shown in the accompanying table. Use Table 2 and Table 4.
ANOVA
df SS MS F Significance F
Regression 2 5,081.3 2,540.7 5.94E-01
Residual 17 80,460.13 4,732.95
Total 19 85,541.40
Coefficients Standard Error t Stat p-value Lower 95% Upper 95%
Intercept 723.66 91.7833 7.8844 0.0000 530.01 917.30
Poverty 2.2587 5.0381 0.4483 0.6596 -8.37 12.89
Income 11.8452 12.8168 0.9242 0.3683 -15.20 38.89
a. Specify the sample regression equation. (Negative values should be indicated by a minus sign. Report your answers to 4 decimal places.)
Crime = 723.6600 + 2.2587 Poverty + 11.8452 Income
b-1. Choose the appropriate hypotheses to test whether the poverty rate and the crime rate are linearly related.
H0: Β1 = 0; HA: Β1 ≠ 0
b-2. At the 5% significance level, what is the conclusion to the hypothesis test?
Do not reject H0; we cannot conclude the poverty rate and the crime rate are linearly related.
c-1. Construct a 95% confidence interval for the slope coefficient of income. (Negative values should be indicated by a minus sign. Round your answers to 2 decimal places.)
Confidence interval -8.37 to 12.89
c-2. Using the confidence interval, determine whether income is significant in explaining the crime rate at the 5% significance level.
Income is not significant in explaining the crime rate, since its slope coefficient does not significantly differ from zero.
d-1. Choose the appropriate hypotheses to determine whether the poverty rate and income are jointly significant in explaining the crime rate.
H0: Β1 = Β2 = 0; HA: At least one Βj ≠ 0
d-2. At the 5% significance level, are the poverty rate and income jointly significant in explaining the crime rate?
Yes, since the null hypothesis is rejected.