Total 200 points
Questions 1-2 (50 points + 50 points = 100 points)
Download the attached gss.sav (data from general social survey). Using SPSS to conduct t-tests
to answer the following questions:
1. Do internet users on average spend 4.5 hours per week on e-mail (variable: emailhrs)?
a. List the null hypothesis and the alternative hypothesis.
b. Use SPSS to run a one-sample t-test and include your SPSS outputs with your
answer.
c. What are the t statistics and p-value of the t-test respectively, according to (b)?
d. Draw your conclusion on whether or not the null hypothesis in (a) should be
rejected (use a 95% significance level), based on (c).
2. Do females and males (variable name: sex) on average spend same hours on e-mail
(variable name: emailhrs)?
a. List the null hypothesis and alternative hypothesis.
b. To test the hypothesis, should you use an independent-sample t-test or a paired-
sample t-test?
c. Use SPSS to conduct the test and include your SPSS outputs with your answer.
d. What are the t statistics and p-value of the t-test respectively, according to (c)?
e. Draw your conclusion on whether or not the null hypothesis should be rejected,
based on the t-test result.
Question 3. (50 points)
Using the attached dataset World_updated.sav. Two of the variables in this file (rgdp86 and
rgdp88) measure real Gross Domestic Product (GDP) per capita in 1986 and 1988 respectively.
Please conduct the appropriate t-test to answer the following question: “Is there statistically
significant evidence that per capita GDP in 1988 is different from that of 1986?
Please show your results and reasoning to justify your answer by answering the following
questions.
a. List the null hypothesis and alternative hypothesis.
b. To test the hypothesis, should you use an independent-sample t-test or paired-sample t-
test?
c. Show your SPSS outputs.
d. What are the t statistics and p-value of the t-test respectively, according to (b)?
f. Draw your conclusion on whether or not the null hypothesis in (a) should be
rejected (use a 95% significance level), based on the t-test result.
Question 4. (50 points)
It is believed that, the average numbers of hours spent studying per day (HOURS) during undergraduate
education should have a positive linear relationship with the starting salary (SALARY, measured in
thousands of dollars per month) after graduation. Given below is the output from regressing starting
salary on number of hours spent studying per day for a sample of 51 students.
Note: The format of the regression results has been purposely changed to be different from SPSS outputs;
some of the numbers in the output are purposely erased
Regression Statistics
Multiple R 0.8857
R Square 0.7845
Adjusted R Square 0.7801
Standard Error 1.3704
Observations 51
ANOVA
df SS MS F Significance F
Regression 1 335.0472 335.0473 178.3859
Residual 1.8782
Total 50 427.0798
Standard
Coefficients Error t Stat P-value Lower 95% Upper 95%
Intercept -1.8940 0.4018 -4.7134 2.051E-05 -2.7015 -1.0865
Hours 0.9795 0.0733 13.3561 5.944E-18 0.8321 1.1269
4.1) Fill in the gap: This simple regression with hours spent studying per day can explain …………. %
variations in starting salary.
4.2) Referring to the table, the estimated average change in salary (in thousands of dollars) as a result of
spending an extra hour per day studying is
A) -1.8940
B) 0.8857
C) 0.9795
D) .7845
4.3) Referring to the table, the value of the measured t-test statistic to test whether average SALARY
depends linearly on HOURS is
A) -4.7134
B) -1.8940
C) 0.9795
D) 13.3561
