Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

Econometrics

Practice Midterm Exam #2

Part I - Multiple Choice (36 points in total – 3 points each)

Place your answers in these boxes:

Question	1	2	3	4	5	6	7	8	9	10	11	12
Answer

1. You are very certain that providing families with subsidized housing improves children’s outcomes. Which study should most change the mean and variance of your beliefs?

A. A randomized trial showing that subsidized housing no impact on children.

B. A randomized trial showing that subsidized housing improves children’s outcomes.

C. A randomized trial showing that subsidized housing hurts children’s outcomes.

D. An observational study showing that subsidized housing hurts children’s outcomes.

2. Does earning an BA at Case Western improve your future income? What theoretically correct counterfactual must you observe to know this?

A. The incomes of students rejected from Case Western.

B. Your income prior to starting the Case.

C. Your income after completing the BA.

D. None of these.

3. Random assignment, if done properly, guarantees that a study has

A. High internal validity

B. High external validity

C. Both A and B

D. Neither A nor B

4. Randomized experiments can be analyzed with bivariate regressions (of the outcome Y on the treatment X) because

A. Outcomes are not correlated with potential omitted variables.

B. Assignment to treatment is not correlated with outcomes.

C. Assignment to treatment is not correlated with potential omitted variables.

D. The sample is representative of the population. 

5. Professor Shoag regresses your midterm score on your Stats midterm score. You turn out to have a positive residual. This means that:

A. Your midterm score is the average score of the whole class.

B. Stats midterm scores are poor predictors of Econometrics midterm scores.

C. You scored lower on this test than last semester’s score would have predicted.

D. You scored higher on this test than last semester’s score would have predicted.

6. In the handedness research that you read, I estimated the following regression:

In (Earnings) = 10.2 - 0.1 LeftHanded

Which of these statements about this regression is correct?

A. Lefties earn 0.1 percent less than righties.

B. Lefties earn 10 percent less than righties.

C. Lefties earn 0.1 percentage points less than righties.

D. Lefties earn 10 percentage points less than righties.

7. In the Michelle Rhee IMPACT case, which control variable was the most important for minimizing the bias in estimates of teachers’ impacts on students’ test scores?

A. Students’ prior year test scores.

B. Students’ current year test scores.

C. Students’ poverty status.

D. Students’ parental education levels.

8. Assume all people have black, brown, blond or red hair. Which of the following regressions immediately tells you whether redheads are smarter than the average non-redhead?

A. 

B. 

C. 

D. 

9. Which is false for a probit model?

A. The dependent variable Y must be a dummy variable.

B. Predicted values from the model fall between 0 and 1.

C. Estimates from the model convey statistical significance clearly.

D. The magnitudes of coefficients from the model can be easily interpreted.  

10. We observe this relationship between weight (pounds) and height (feet) in data on adults:

Which statement is true?

A. Each additional foot of height is associated with 30 pounds more of weight.

B. Each additional foot of height is associated with 34 pounds more of weight.

C. On average, 6-foot tall people weigh 32 pounds more than 5-foot tall people.

D. On average, 6-foot tall people weigh 52 pounds more than 5-foot tall people.

11. You run a linear probability model on a sample of Americans, regressing an indicator for gun ownership on income (measured in tens of thousands of dollars). You find a coefficient of 0.06 on income, with a standard error of 0.04. You can conclude that:

A. An additional $10,000 of income is associated with a 0.06 percentage point increase in the probability of owning a gun, a relationship that is statistically significant.

B. An additional $10,000 of income is associated with a 0.06 percentage point increase in the probability of owning a gun, a relationship that is statistically insignificant.

C. An additional $10,000 of income is associated with a 6 percentage point increase in the probability of owning a gun, a relationship that is statistically significant.

D. An additional $10,000 of income is associated with a 6 percentage point increase in the probability of owning a gun, a relationship that is statistically insignificant.

12. Data reveal the following relationship between life expectancy (years) and gender, the number of days per week a person exercises, and the interaction of gender and exercise:

 

Each additional day of exercise per week is associated with life expectancy

A. Increasing by 2 years for women and increasing 3 years for men.

B. Increasing by 2 years for women and increasing 5 years for men.

C. Increasing by 3 years for women and decreasing 5 years for men.

D. Increasing by 3 years for women and increasing 3 years for men.

Part II – Short Answers (35 points in total – 5 points each)

One of the Millennium Development Goals was to reduce child mortality by two-thirds by 2015 (compared to 1990). To achieve this goal, many governments increased their expenditures on public health. How much does a given increase in public health expenditure reduce child mortality? The answer to this question may help guide policymakers’ decisions about how much of a government’s budget should be allocated toward such investments.

Suppose a group of researchers decided to investigate this question using observational data. They used a sample of 148 countries from the year 2000. Below are a description of the variables they used, summary statistics, and their regression results.

Table 1 – Description of Variables

Table 2 – Regression Results

Dependent Variable: childmort

INSTRUCTIONS: All questions refer to Table 2.

1. Write down the sample regression function represented by regression (1). What is the predicted child mortality rate of a country that spends 5 percent of GDP on public health expenditures?

2. Interpret the coefficient on healthexp in regression (1). Is that coefficient statistically significant? Show your calculation and explain your conclusion in a language specific to this context.

3. Write down the sample regression function represented by regression (2). Interpret the coefficient on democratic in regression (2).

4. What is the bias that results from omitting democratic status as a control variable? Explain whether that omission causes us to over- or under-estimate the impact of public health expenditures on child mortality?

5. Do democratic countries spend more or less than non-democratic countries on public health? Explain how you conclude this from the formula for omitted variable bias.

6. Based only on the three regressions in Table 2, do you think public health expenditures reduce child mortality? Explain.

7. Why is generating extremely convincing causal evidence on this question difficult?

For course staff only: