William H. Knapp III

You will not be able to submit your work for credit, because you are not logged in. Log in!

This homework was due on Monday, December 31 at 06:00 a.m. Turkish time. Late submissions receive half credit.

By checking the box below, you certify that the answers you will submit here represent your own work.

1. Someone who is primarily interested in the partial regression coefficients is probably most interested in using MRC for what purpose?
Prediction
Understanding
Both

2. Imagine a lawyer is trying to establish that some company has engaged in discriminative salary policies based on ethnicity after controlling for variables like seniority, job type, etc. What should the lawyer be most interested in?
The coefficient of determination (i.e. Big R-squared)
Correlation coefficients
Partial correlation coefficients
The regression constant
All of the above

3. The process of performing multiple multiple regressions and testing to see which variable should be included or removed based on its significance is known as.
Correlation
Multiple regression
Simple linear regression
Stepwise regression

4. The Chi-square distribution depends on which of the following:
Correlation
Degrees of Freedom
Mean
Variance
All of the above

5. The Chi-square can be used to test hypotheses about whether some variable has a particular distribution shape.
True
False

6. The Chi-square can be used to test hypotheses about whether two variables vary independently from one another.
True
False

7. What is the correct formula for the chi-square?

$$\frac{(O-E)}{E}$$

$$\frac{(O-E)}{O}$$

$$\sum{\frac{(O-E)}{E}}$$

$$\sum{\frac{(O-E)}{O}}$$

$$\frac{(O-E)^2}{E}$$

$$\frac{(O-E)^2}{O}$$

$$\sum{\frac{(O-E)^2}{E}}$$

$$\sum{\frac{(O-E)^2}{O}}$$

8. What would be better than using a Chi-square test to see if the frequencies of two groups differed from some hypothetical distribution?
ANOVA
Binomial test
Multinomial test
t-test
z-test

9. What would be better than using a Chi-square test to see if the frequencies of five groups differed from some hypothetical distribution?
ANOVA
Binomial test
Multinomial test
t-test
z-test

10. The degrees of freedom for a Chi-square test of independence are found similarly to degrees of freedom for what other test?
ANOVA for the interactions of some variables
ANOVA for the main effect of some variable
correlation
t-test

11. Imagine you wanted to see if there was a differences in how conservative different Muslim women perceive themselves to be. You think that Muslim women wear headscarves will view themselves as more conservative than their non-covered counterparts. To test this you survey a number of women on the streets of Istanbul and ask them to indicate whether they view themselves as liberal, moderate, or conservative. You also note whether or not each woman is wearing a headscarf. Because your interest is only in differences of perception between Muslim women you don't include any data from women who didn't identify themselves as Muslim in the survey. Your data are below:
24 Muslim women who wore a headscarf identified as liberal.
38 Muslim women who wore a headscarf identified as moderate.
32 Muslim women who wore a headscarf identified as conservative.
37 Muslim women who did not wear a headscarf identified as liberal.
42 Muslim women who did not wear a headscarf identified as moderate.
34 Muslim women who did not wear a headscarf identified as conservative.
How many Muslim women were included in the survey in total?

12. Continuing from the previous question, what percent of Muslim women wore headscarves?
NOTE: I asked for a percentage, this should range from 0-100 not 0-1.

13. If the decision to wear a headscarf is independent of how conservative one perceives themselves to be, what percent of the Muslim women who identified as liberal should wear headscarves?
NOTE: I asked for a percentage, this should range from 0-100 not 0-1.

14. What percent of Muslim women identified themselves as liberal?
NOTE: I asked for a percentage, this should range from 0-100 not 0-1.

15. If the decision to wear a headscarf is independent of how conservative one perceives themselves to be, what percent of Muslim women would you expect to identify as liberal and wear headscarves?
NOTE: I asked for a percentage, this should range from 0-100 not 0-1.

16. If the decision to wear a headscarf is independent of how conservative one perceives themselves to be, how many Muslim women in your survey would you expect to identify as liberal and wear headscarves?
NOTE: I am not asking for a percentage here.

17. How many degrees of freedom should you use for your Chi-square test?

18. Using an alpha of .01, what is the critical value for the Chi-square test?
HINT: qchisq!

19. What's the value of Chi-square for your test?

20. What's the probability of observing a Chi-square that or more extreme?
HINT: pchisq!