difference in difference models

1

Difference in Difference Models

Bill EvansSpring 2008

2

Difference in difference models

• Maybe the most popular identification strategy in applied work today

• Attempts to mimic random assignment with treatment and “comparison” sample

• Application of two-way fixed effects model

3

Problem set up

• Cross-sectional and time series data• One group is ‘treated’ with intervention• Have pre-post data for group receiving

intervention• Can examine time-series changes but,

unsure how much of the change is due to secular changes

4time

Y

t1 t2

Ya

Yb

Yt1

Yt2

True effect = Yt2-Yt1

Estimated effect = Yb-Ya

ti

5

• Intervention occurs at time period t1

• True effect of law– Ya – Yb

• Only have data at t1 and t2

– If using time series, estimate Yt1 – Yt2

• Solution?

6

Difference in difference models

• Basic two-way fixed effects model– Cross section and time fixed effects

• Use time series of untreated group to establish what would have occurred in the absence of the intervention

• Key concept: can control for the fact that the intervention is more likely in some types of states

7

Three different presentations

• Tabular• Graphical• Regression equation

8

Difference in Difference

BeforeChange

AfterChange Difference

Group 1(Treat)

Yt1 Yt2 ΔYt

= Yt2-Yt1

Group 2(Control)

Yc1 Yc2 ΔYc

=Yc2-Yc1

Difference ΔΔYΔYt – ΔYc

9time

Y

t1 t2

Yt1

Yt2

treatment

control

Yc1

Yc2

Treatment effect=(Yt2-Yt1) – (Yc2-Yc1)

10

Key Assumption

• Control group identifies the time path of outcomes that would have happened in the absence of the treatment

• In this example, Y falls by Yc2-Yc1 even without the intervention

• Note that underlying ‘levels’ of outcomes are not important (return to this in the regression equation)

11time

Y

t1 t2

Yt1

Yt2

treatment

control

Yc1

Yc2

Treatment effect=(Yt2-Yt1) – (Yc2-Yc1)

TreatmentEffect

12

• In contrast, what is key is that the time trends in the absence of the intervention are the same in both groups

• If the intervention occurs in an area with a different trend, will under/over state the treatment effect

• In this example, suppose intervention occurs in area with faster falling Y

13time

Y

t1 t2

Yt1

Yt2

treatment

control

Yc1

Yc2

True treatment effect

Estimated treatment

TrueTreatmentEffect

14

Basic Econometric Model

• Data varies by – state (i)– time (t)– Outcome is Yit

• Only two periods• Intervention will occur in a group of

observations (e.g. states, firms, etc.)

15

• Three key variables– Tit =1 if obs i belongs in the state that will

eventually be treated– Ait =1 in the periods when treatment occurs

– TitAit -- interaction term, treatment states after the intervention

• Yit = β0 + β1Tit + β2Ait + β3TitAit + εit

16

Yit = β0 + β1Tit + β2Ait + β3TitAit + εit

BeforeChange

AfterChange Difference

Group 1(Treat)

β0+ β1 β0+ β1+ β2+ β3 ΔYt

= β2+ β3

Group 2(Control)

β0 β0+ β2 ΔYc

= β2

Difference ΔΔY = β3

17

More general model

• Data varies by – state (i)– time (t)– Outcome is Yit

• Many periods• Intervention will occur in a group of states

but at a variety of times

18

• ui is a state effect

• vt is a complete set of year (time) effects• Analysis of covariance model

• Yit = β0 + β3 TitAit + ui + λt + εit

19

What is nice about the model

• Suppose interventions are not random but systematic– Occur in states with higher or lower average Y– Occur in time periods with different Y’s

• This is captured by the inclusion of the state/time effects – allows covariance between – ui and TitAit

– λt and TitAit

20

• Group effects – Capture differences across groups that are

constant over time• Year effects

– Capture differences over time that are common to all groups

21

Meyer et al.

• Workers’ compensation– State run insurance program– Compensate workers for medical expenses

and lost work due to on the job accident• Premiums

– Paid by firms– Function of previous claims and wages paid

• Benefits -- % of income w/ cap

22

• Typical benefits schedule– Min( pY,C)– P=percent replacement– Y = earnings– C = cap

– e.g., 65% of earnings up to $400/month

23

• Concern: – Moral hazard. Benefits will discourage return to work

• Empirical question: duration/benefits gradient• Previous estimates

– Regress duration (y) on replaced wages (x)• Problem:

– given progressive nature of benefits, replaced wages reveal a lot about the workers

– Replacement rates higher in higher wage states

24

• Yi = Xiβ + αRi + εi

• Y (duration)• R (replacement rate)• Expect α > 0• Expect Cov(Ri, εi)

– Higher wage workers have lower R and higher duration (understate)

– Higher wage states have longer duration and longer R (overstate)

25

Solution

• Quasi experiment in KY and MI• Increased the earnings cap

– Increased benefit for high-wage workers • (Treatment)

– Did nothing to those already below original cap (comparison)

• Compare change in duration of spell before and after change for these two groups

26

27

28

Model

• Yit = duration of spell on WC

• Ait = period after benefits hike

• Hit = high earnings group (Income>E3)

• Yit = β0 + β1Hit + β2Ait + β3AitHit + β4Xit’ + εit

• Diff-in-diff estimate is β3

29

30

Questions to ask?

• What parameter is identified by the quasi-experiment? Is this an economically meaningful parameter?

• What assumptions must be true in order for the model to provide and unbiased estimate of β3?

• Do the authors provide any evidence supporting these assumptions?