Consider the following quasi-experiment to st using data from fast food restaura

Question

Consider the following quasi-experiment to st using data from fast food restaurants. In 1992, there was an increase in the (state) 2. udy the effects of minimum wages on employment minimum age in one U.S. state (New Jersey) but not in neighboring locations (Eastern Pennsylvania). To calculate the 1ff in diff the control group. To do this, the study provides you with the following information you need the change in the treatment group and the change in PA FTE Employment 23.33 NI 20.44 before FTE Employment after21.17 21.03 Where FTE is full time equivalent" and the numbers are average employment per restaurant. (a) [2 Points] Calculate the change in the treatment group, the change in the control group, and finally Byilf-in-difs, Since minimum wages represent a price floor, did you expect (b) [1 Point] If you look at liff in diffs, is this number primarily due to a change in the (c) [1 Point] The standard error for lif-in-cliffs is 1.76. Test whether or not the coefficient or negative? treatment group or the control group? Is this what you expected? is statistically significant. What do these results suggest about the effect of a small minimum wage increase on employment?

Explanation / Answer

ans.

a. Quasi-experiment approach is mainly used to evaluate the impact of variuos programs. and in quasi-experiment method we need treatment group and the control group

Here in our case, it shows the the welfare effects of a minimum wage increase where one could track workers from a point in time before the increase to another point sufficiently after.

here we have the effects of minimum wage increase before and after .

Treatment group : those earning minimum wage (New Jersey)

Control group : those earning above the minimum wage (the neighbouring state Pennsylvania)

So after a minimum wage increase, is there a significant difference in the average employment per restaurant between those earning the minimum wage (the treatment group) and those earning above the minimum wage (the control group).

b. We have to estimate the difference in the changes of the employment in the two states - the difference in difference

we estmate the following regression

U = [eta] 0 + [eta] 1T + [eta] 2NJ + [eta] 3(T*NJ) + e

here U = rate of unemployment in each state

T = time dummy for before and after minimum wage increase and NJ = state summy for NJ

[eta] 0 = rate of unemployment in PA before the minimum wage increase

[eta] 1 = change in rate of unemployment in PA

[eta] 2 = difference in the two states unemployment rate before the increase in minimum wage

[eta] 3 = difference in difference (difference between the changes in two states)

PA

NJ

Difference

FTE before

23.33

20.44

-2.89

FTE after

21.17

21.03

-0.14

Change

-2.16

0.59

2.75

[eta hat{hat{}}] 0 = 23.33,    [eta hat{hat{}}] 1 = 21.17-23.33 = -2.16 [eta hat{hat{}}] 2 = 20.44-23.33 = -2.89

and [eta hat{hat{}}] 3 = (21.03 - 20.44) - (21.17 - 23.33) = 0.59 - (-2.16) = 2.75

so [eta hat{hat{}}] diff-indiff = 2.75

we can read it like employment rose in NJ relative to PA after the minimum wage increase.

since minimum wage represents price floor, [eta hat{hat{}}] diff-indiff has to be positive.

c). the SE for [hat{eta} hat{}] 1diffs in-diffs = 1.36 and T = 1.96

t-test statistics = (2.76-1.96)/1.36 = 0.5882

the result is statistically siginificant at 5% level of significance

yes, it would have disouraged me if it was not statistically significant, given that benifit from minimum wage increase has outweighed the cost of employment loss

Related Questions

Navigate

• Browse (All)
• Browse C
• Subjects

---