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

ASSIGNMENT 1: DIFFERENCE-IN-DIFFERENCES AND SYNTHETIC CONTROL METHODS

Due Date: March 4, 2024

Please submit your assignment individually. If you collaborated with classmates, include the names of all group members in your submission; however, groups must not exceed five members. For any questions where Stata has been used, please include all the generated figures and tables, and make sure to attach the corresponding Stata log file to the end of your assignment

1 The Impact of the Mariel Boatlift on the Miami Labor Market

A primary focus of the immigration debate centers on how immigration affects the employment opportunities of native-born workers. More specifically, when there is a sudden influx of immigrants, what are the immediate effects on the wages and employment of local workers in the host country? Consider the simplest model of labor demand and labor supply, assuming that immigrants and natives are perfect substitutes in productions and compete for the same types of jobs. Under this model, an increase in immigrant workers would shift out the labor supply curve, leading to a decrease in the equilibrium wage an an increase in total employment. However, the lower wage would result in fewer native-born workers participating in the labor market.

A critical contribution to this discussion is the 1990 study by David Card (Card, 1990), a 2021 Nobel Prize laureate and a Queen’s alumnus. This study highlights how the predictions of the canonical labor demand and supply model may not work well in reality. While this study is profoundly influential, it does have some methodological limitations. Consequently, researchers have continued to explore the question, seeking new data sources and refining the methodology (Borjas, 2017; Peri and Yasenov, 2019).

The first part of the assignment asks you to read Card (1990) and answer the following questions:

1. Write a concise summary of Card (1990), covering the research question, main contribution(s), data, empirical method, and the key findings. The summary should not be longer than 1 page using a font size of 12 and single spacing.

2. Write down the econometric model to estimate the effect of the Mariel Boatlift on log hourly wages using the difference-in-differences approach. Make sure to clearly specify the meaning of each variable used in the regression equation.

3. What is the key identifying assumption of the difference-in-differences (DID) approach in this specific context of study?

4. Suppose you now have access to the dataset used in Card (1990)’s study. In addition, you can access Current Population Survey data dating back to 1972, which provide information similar to that in Card (1990)’s dataset. Using the extra data sources, can you describe a way to test the validity of the DID assumption?

5. Describe how the synthetic control method could potentially improve upon the DID approach to study the causal effect of the Mariel Boatlift on the Miami labor market.

6. Outline the procedures to implement the synthetic control method for this research question.

2 The Effect of California’s Tobacco Control Program

In Lecture 10, we illustrated the synthetic control method using an application in the study by Abadie et al. (2010), which evaluates the effect of California’s tobacco control program in 1988 on tobacco consumption. In this part of the assignment, you are asked to use Abadie et al. (2010)’s data (smoking.dta) to reproduce some of the paper’s results, applying an alternative specification.

1. What is the benefit of using the synthetic control method to choose the comparison group for California instead of using the rest of the U.S. in this application? Illustrate your answer with the data.

2. Abadie et al. (2010)’s predictors of smoking prevalence are: average retail price of cigarettes, log per capita state personal income, the percentage of the population aged 15–24, and per capita beer consumption. These variables are averaged over the 1980–1988 period. They further add three years of pre-intervention smoking consumption (1975, 1980, and 1988) as predictors.

In this question, you are asked to implement an alternative way to construct the synthetic control group. Specifically, predictors of smoking prevalence are: average retail price of cigarettes, log per capita state personal income, the percentage of the population aged 15–24, and per capita beer consumption. These variables are averaged over the entire pre-intervention period. We further add pre-intervention smoking consumption for each pre-intervention period as predictors.

Reproduce Table 2, Figure 2, and Figure 3 of Abadie et al. (2010) based on this alternative way of constructing the synthetic control. Compare the results with those presented in the paper.

3. Now, let’s consider a placebo test, in which we pretend the treated state is Texas, rather than California. Now, construct the synthetic control group for the “treated” unit Texas using the approach described in part 2, and reproduce Figure 2.

4. Repeat part 3, pretending that the treated state is Pennsylvania.

5. Repeat part 3, pretending that the treated state is Alabama.

6. Reproduce Figure 3, presenting the per-capita cigarette sales gaps in California (obtained in part 2) and the placebo gaps (obtained in parts 3–5).

7. How can the results from parts 3–6 (or more similar placebo tests) help you evaluate the significance of the synthetic control estimate of the effect of the California’s tobacco control program?

References

Abadie, Alberto, Alexis Diamond, and Jens Hainmueller (2010), “Synthetic control methods for comparative case studies: Estimating the effect of california’s tobacco control program.” Journal of the American statistical Association, 105, 493–505.

Borjas, George J (2017), “The wage impact of the marielitos: A reappraisal.” Industrial and Labor Relations Review, 70, 1077–1110.

Card, David (1990), “The impact of the mariel boatlift on the miami labor market.” Industrial and Labor Relations Review, 43, 245–257.

Peri, Giovanni and Vasil Yasenov (2019), “The labor market effects of a refugee wave: Synthetic control method meets the mariel boatlift.” Journal of Human Resources, 54, 267–309.