In: Statistics and Probability
For Questions 3-6, refer to the following: A study was conducted
with 52 undergraduates at Texas A&M University. The variables
measured refer to the parents of these students. The response
variable (y) is the number of children that the parents have. The
explanatory variable (x) is the mother’s educational level,
measured as her number of years of formal education. For these
data, X bar = 9.88, r = -0.356 , the prediction equation is y bar =
5.40-0.207x , the standard error of the slope estimate (seb) is
0.079, and the SSE = 201.95.
3)Calculate the r2 from the information provided above, and
interpret it with respect to variability explained and reduction in
error.
4)Test the null hypothesis that the population slope = 0, and
estimate the p-value (or a range for the P-value). Would you reject
the null hypothesis (if alpha=0.05)?
H0:
Ha:
t statistic:
Estimated p-value:
Reject null hypothesis?
5)What is the 95% confidence interval for , and how would you
interpret this confidence interval?
6)Test the null hypothesis that the population correlation = 0.
What are the null and alternative hypotheses? Calculate the t test
statistic. You can use the estimate of r provided in the
description of the study. In the bivariate case, the test statistic
for should be equal (plus or minus rounding error) to the test
statistic for what other parameter?
H0:
Ha:
t statistic:
Test statistic for should be equal (plus or minus rounding error)
to the test statistic for what other parameter?
7) Given your response to Question 6, what is the p-value (or a range for the P-value) associated with the test statistic for the population correlation? Would you reject the null hypothesis with an alpha of 0.05? Estimate of p-value associated with test statistic in Question 6:Reject null hypothesis?