1.) What is the causal link the paper is trying to reveal?
- Impact of minimum wage increases on employment ## 2.) What would be the ideal experiment to test this causal link?
- An ideal way to experimentally test this causal link is to randomly assign areas with minimum wage increases. Ideally any differences in employment would be due to minimum wage increases. ## 3.) What is the identification strategy?
- Card and Krueger use a differences in differences approach to test for differences in employment before and after the law changed in New Jersey and Pennsylvania. The authors used baseline data to show that Pennsylvania and New Jersey were similar before the wage change in New Jersey. ## 4.) What are the assumptions / threats to this identification strategy? (answer specifically with reference to the data the authors are using)
- The first assumption of this identification is that New Jersey and Pennsylvania would be similar/identical enough and that without the minimum wage law change in New Jersey, there would be no significant differences between the two states. The authors showed this in their baseline data where only the price of full meal was significantly different. Threats to this identification strategy is that New Jersey and Pennsylvania do not satisfy the parallel trends and that the differences found post treatment are not related to the minimum wage, but other factors.
minWage<-read.csv('./CardKrueger1994_fastfood.csv')
minWage<-as.data.table(minWage)
for(i in 1:nrow(minWage)){
if(minWage$state[i]==1){
minWage$state[i]='zNJ'
}
if(minWage$state[i]==0){
minWage$state[i]='PA'
}
}
|
|
|
Statistic
|
N
|
Mean
|
St. Dev.
|
Min
|
Pctl(25)
|
Pctl(75)
|
Max
|
|
|
|
mean_emptot
|
2
|
21.885
|
2.045
|
20.439
|
21.162
|
22.608
|
23.331
|
|
mean_emptot2
|
2
|
21.097
|
0.098
|
21.027
|
21.062
|
21.131
|
21.166
|
|
mean_bk
|
2
|
42.696
|
2.274
|
41.088
|
41.892
|
43.500
|
44.304
|
|
mean_roys
|
2
|
23.146
|
2.301
|
21.519
|
22.333
|
23.960
|
24.773
|
|
mean_wendys
|
2
|
16.291
|
3.813
|
13.595
|
14.943
|
17.639
|
18.987
|
|
mean_wage_st
|
2
|
4.621
|
0.013
|
4.612
|
4.617
|
4.626
|
4.630
|
|
mean_wage_st2
|
2
|
4.849
|
0.328
|
4.617
|
4.733
|
4.965
|
5.081
|
|
|
#Diff in employment and Wages
minWage$dwage=minWage$wage_st-minWage$wage_st2
demp<-lm(demp~state, data=minWage)
stargazer(demp,type='html')
|
|
|
|
Dependent variable:
|
|
|
|
|
|
demp
|
|
|
|
statezNJ
|
2.750**
|
|
|
(1.154)
|
|
|
|
|
Constant
|
-2.283**
|
|
|
(1.036)
|
|
|
|
|
|
|
Observations
|
384
|
|
R2
|
0.015
|
|
Adjusted R2
|
0.012
|
|
Residual Std. Error
|
8.968 (df = 382)
|
|
F Statistic
|
5.675** (df = 1; 382)
|
|
|
|
Note:
|
p<0.1; p<0.05; p<0.01
|
I got 2.75 for the difference in differences estimator on matching , This is nearly identical to theirs but the standard error in my model is smaller. d.) The model I would use for the difference in differences estimator would be Employment=beta_0+beta_1 Time + beta2* Treatment + Beta4 Treatment*Time and beta4 would be our difference in differences estimator.
colnames(minWage)<-c('id','state','emptot.1','emptot.2','demp','chain','bk','kfc','roys','wendys','wage_st.1','wage_st.2','dwage')
long<-reshape(minWage, direction='long',
varying=c('emptot.1', 'wage_st.1', 'emptot.2','wage_st.2'),
timevar='time',
times=c('1','2'),
v.names=c('emptot','wage'),
idvar=c('id','state'))
long$treat=0
for(i in 1:nrow(long)){
if(long$state[i]=='zNJ'){
long$treat[i]=1
}
}
did<-lm(emptot~time+treat+time*treat,data=long)
stargazer(did,type='html')
|
|
|
|
Dependent variable:
|
|
|
|
|
|
emptot
|
|
|
|
time2
|
-2.166
|
|
|
(1.516)
|
|
|
|
|
treat
|
-2.892**
|
|
|
(1.194)
|
|
|
|
|
time2:treat
|
2.754
|
|
|
(1.688)
|
|
|
|
|
Constant
|
23.331***
|
|
|
(1.072)
|
|
|
|
|
|
|
Observations
|
794
|
|
R2
|
0.007
|
|
Adjusted R2
|
0.004
|
|
Residual Std. Error
|
9.406 (df = 790)
|
|
F Statistic
|
1.964 (df = 3; 790)
|
|
|
|
Note:
|
p<0.1; p<0.05; p<0.01
|
Using the DiD equation from part 2 question d, I get a change in employment of 2.754. THis means that the increase in minimum wage from New Jersey caused a 2.754 percent increase in total employment.