Problem Set 4 Solved

Description

Question 1- Minimum Wages and Employment (60 points)

In this problem set, you are expected to replicate some of the main results of an in uential paper by David Card and Alan Krueger:

David Card and Alan Krueger. “Minimum Wages and Employment: A Case Study of the Fast Food Industry in New Jersey and Pennsylvania.” American Economic Review 84 (September 1994). (http://davidcard.berkeley.edu/papers/njmin-aer.pdf)

Check this youtube video for the discussion on minimum wage: https://youtu.be/mWwXmH-n5Bo?t=318

The data set used in the paper is available at SUCourse+: “Datasets > card krueger data.dta”.

Some Tips for replication:

First you need to generate full time employment variables (as described in the paper) for both time periods.

In Table 3, in order to obtain the standard errors for the 3rd column, you can use “ttest” command in STATA. Check the help le for “ttest” to see how to use it.

In Table 4, note that the dependent variable is the di erence in full time employment in both periods. Therefore, you need to generate a new variable indicating that di erence.

In Table 4 and Table 7, use if condition at the end of your regression commands in order to limit the sample as described in the paper (note that the authors are not using the observations for which the wage information is missing).

In Table 7, rst you need to generate the price variables (as described in the paper) indicating the prices in both periods. These price variables are used to calculate the dependent variable in Table 7. Note that, in Table 7, the authors use the

sample for which the wage and fte information is not missing.

1. What is the main research question of the paper? Discuss the importance (policy implications) of this research question. Brie y describe the data and the methodology used to answer this research question? (10 points)

2. Using the data (card krueger data.dta), calculate the following statistics which are reported in Table 3 in the paper (Read the related text and the table notes carefully in order understand how the authors obtained these statistics. Hint: In order to calculate the standard error for the mean di erences, you can use “ttest” command in STATA.). Discuss what these statistics indicate. Based on these statistics, what is the estimated impact of minimum wage increase on full time employment in NJ? (15 points)

3. Using the data, replicate the following statistics which are reported in Table 4 in the paper (Read the related text and the table notes carefully in order understand how the authors obtained these statistics. There might be small di erences between your results and the paper. It is acceptable if you obtain coe cient estimates of around 2.28 instead of 2.33 and 2.30.). Write the empirical model that is estimated in column (ii). Discuss the meaning of the coe cient of “New Jersey dummy” in column (ii). What is the main advantage of speci cation in column (ii), as compared to the simple calculations in question (2). (20 points)

4. Replicate the following statistics which are reported in Table 7 in the paper (Read the related text and the table notes carefully in order understand how the authors obtained these statistics.). What is the research question in this analysis? Discuss the meaning of the coe cient of “New Jersey dummy” in column (ii). (15 points)

Question 2 – Impact of Tra c Laws (15 points)

Use the data in TRAFFIC2.DTA for this exercise.

1) Run an OLS regression of prcfat on a linear time trend, monthly dummy variables, and the variables wkends, unem, spdlaw, and beltlaw. Discuss your ndings (Interpret the size and signi cance of the estimated coe cients. While discussing the results for month dummies, mention only the min. and max. coe cients of month dummies.)

Question 3 – Policy Analysis (25 points)

Use the data in INJURY.DTA for this exercise.

1. Using the data for Kentucky, reestimate equation (13.12) in the book, adding as explanatory variables male, married, and a full set of industry and injury type dummy variables. Interpret the estimated coe cient for “afchnge” , “highearn” and “afchnge highearn” variables. What do your results imply

about the impact of policy?(10 points)

2. What do you think about the small R-squared from part (1)? Does this mean the equation is useless? (5 points)

2. Estimate equation (13.12) using the data for Michigan. Compare the estimates on the interaction term for Michigan and Kentucky. Is the Michigan estimate statistically signi cant? How do you explain the di erent results (in terms of signi cance) for Kentucky and Michigan? (10 points)

5