Download and go over this seminal paper by David Card and Alan Krueger. Card and Krueger (1994) Minimum Wages and Employment: A Case Study of the Fast-Food Industry in New Jersey and Pennsylvania AER 84(4): 772-793. Be careful: They released a 2000 follow up with the exact same title followed by “:Reply”. We want the original, not the follow-up. Briefly answer these questions:
a. What is the causal link the paper is trying to reveal?
Answer:
The causal link in this paper is the minimum wage effect on the establishment-level employment outcomes.
b. What would be the ideal experiment to test this causal link?
Answer:
The ideal experiment to test the causal link is to randomly assign establishment-level employees into different groups with different levels of minimum wages and observe their employment outcomes differences.
c. What is the identification strategy?
Answer:
The identification strategy in this paper is to survey fast-food restaurants in New Jersey and eastern Pennsylvania for two waves. In the first wave, they asked questions on employment, starting wages and other characteristics. In the second wave with increased minimum wage, they asked same questions and observe answers for same people who were in the first wave survey.
d. What are the assumptions / threats to this identification strategy? (answer specifically with reference to the data the authors are using)
Answer:
The assumptions are that fast-food stores can typically represent the situation of low-wage workers and have homogeneous requirement. So, we can assume that there are no big difference except minimum wage increase between first wave and second wave. If the PA and NJ have big difference in fast-food restaurants, the identification strategy would fail.
a. Load data from Card and Krueger AER 1994 You can load it directly from my website here. Variable names are self-explanatory if you read the paper.
library(reshape2);
library(stargazer);
library(foreign);
library(knitr);
hw5<-read.csv("CardKrueger1994_fastfood.csv",header=TRUE, row.names=NULL)b. Verify that the data is correct Reproduce the % of Burger King, KFC, Roys, and Wendys, as well as the FTE means in the 2 waves. (Note: This is just to force you to do a summary stats table with R. I used group_by then %>% then summarize. I’m sure some of you will find better ways to do it.)
library(dplyr)
sum(hw5$state) ## [1] 331### Percentage of each restaurant in each state (PA state=0; NJ state=1)
percent<-hw5 %>% group_by(state) %>%summarize(.bk=sum(bk),.kfc=sum(kfc),.roys=sum(roys),.wendys=sum(wendys))
percent$.bk<-100*percent$.bk/(percent$.bk+percent$.kfc+percent$.roys+percent$.wendys);
percent$.kfc<-100*percent$.kfc/(percent$.bk+percent$.kfc+percent$.roys+percent$.wendys);
percent$.roys<-100*percent$.roys/(percent$.bk+percent$.kfc+percent$.roys+percent$.wendys);
percent$.wendys<-100*percent$.wendys/(percent$.bk+percent$.kfc+percent$.roys+percent$.wendys);
percent## # A tibble: 2 x 5
## state .bk .kfc .roys .wendys
## <int> <dbl> <dbl> <dbl> <dbl>
## 1 0 44.3 13.6 18.9 16.3
## 2 1 41.1 28.8 41.6 28.7### FTE mean (PA state=0; NJ state=1)
FTE<-hw5 %>% group_by(state)%>%summarize(.first=mean(emptot,na.rm=TRUE),.second=mean(emptot2,na.rm=TRUE))
FTE## # A tibble: 2 x 3
## state .first .second
## <int> <dbl> <dbl>
## 1 0 23.3 21.2
## 2 1 20.4 21.0c. Use OLS to obtain their Diff-in-diff estimator (almost – you won’t get it exactly) Comment on how your OLS compared to the DiD estimate in Table 3 of the paper.
did<-lm(demp~state,data=hw5)
stargazer(did, type = "html",
title = "Regression results")| Dependent variable: | |
| demp | |
| state | 2.750** |
| (1.154) | |
| Constant | -2.283** |
| (1.036) | |
| Observations | 384 |
| R2 | 0.015 |
| Adjusted R2 | 0.012 |
| Residual Std. Error | 8.968 (df = 382) |
| F Statistic | 5.675** (df = 1; 382) |
| Note: | p<0.1; p<0.05; p<0.01 |
Answer:
The result is similar with the DiD estimate in Table 3 of the paper. The DiD estimate in Table 3 is 2.76, while our OLS estimate is 2.75 which is a little bit lower than 2.76. The standard deviation of the estimate is 1.15 which is close to the table result.
d. What would be the equation of a standard “difference in difference” regression? Just write down the equation.
Answer:
\(D_t\) is the dummy variable of average minimum wage increase.
\[ EMP_{it} = b_0+b_1State_s +b_2D_t +b_3D_tState_s + \epsilon_{it} \]