+ - 0:00:00
Notes for current slide
Notes for next slide

A Difference-in-Differences Approach
using Mixed-Integer Programming Matching

Magdalena Bennett
McCombs School of Business, UT Austin

AEFP 46th Annual Conference
Mar 19, 2021

Diff-in-Diff as an identification strategy

Diff-in-Diff as an identification strategy

Diff-in-Diff as an identification strategy

What about parallel trends?

  • Can matching help solve this?

    • It's complicated (?) (Zeldow & Hatfield, 2019;Lindner & McConnell, 2018; Daw & Hatfield, 2018 (x2); Ryan, 2018; Ryan et al., 2018)
  • Most work has focused on matching outcomes

This paper

  • Identify contexts when matching can recover causal estimates under violations in the parallel trend assumption.

  • Use mixed-integer programming matching (MIP) to balance covariates directly.

  • Matching for panel and repeated cross-sectional data.

This paper

  • Identify contexts when matching can recover causal estimates under violations in the parallel trend assumption.

  • Use mixed-integer programming matching (MIP) to balance covariates directly.

  • Matching for panel and repeated cross-sectional data.


Simulations:
Different DGP scenarios

Application:
School segregation & vouchers

Let's get started

DD Setup

  • Let Yit(z) be the potential outcome for unit i in period t under treatment z.

  • Intervention implemented in T0 No units are treated in tT0

  • Difference-in-Differences (DD) focuses on ATT for t>T0: ATT=E[Yit(1)Yit(0)|Z=1]

  • Assumptions for DD:

    • Parallel-trend assumption (PTA)

    • Common shocks

    E[Yi1(0)Yi0(0)|Z=1]=E[Yi1(0)Yi0(0)|Z=0]

DD Setup (cont.)

  • Under these assumptions: τ^DD=E[Yi1|Z=1]E[Yi1|Z=0]Δpost(E[Yi0|Z=1]E[Yi0|Z=0])Δpre

    • Where t=0 and t=1 are the pre- and post-intervention periods, respectively.

    • Yit=Yit(1)Z+Yit(0)(1Z) is the observed outcome.

Violations to the PTA

  • Under PTA, g1(t)=g0(t)+h(t), where:

    • gz(t)=E[Yit(0)|Z=z,T=t]
    • h(t)=α
  • Bias in a DD setting depends on the structure of h(t).

Two distinct problems when combining matching + DD

  • Regression to the mean:

    • Both groups come from different populations
    • Particularly salient when matching on previous outcomes
  • Bias when matching on time-varying covariates:

    • Depends on the structure of time variation

Simulations

Different scenarios

S1: Time-invariant covariate effect

S2: Time-varying covariate effect

S3: Treatment-independent covariate

S4: Parallel evolution

S5: Evolution differs by group

S6: Evolution diverges in post

Following Zeldow & Hatfield (2019)

Different scenarios

S1: Time-invariant covariate effect

S2: Time-varying covariate effect

S3: Treatment-independent covariate

S4: Parallel evolution

S5: Evolution differs by group

S6: Evolution diverges in post

Following Zeldow & Hatfield (2019)

Parameters:

Parameter Value
Number of obs (N) 1,000
Pr(Z=1) 0.5
Time periods (T) 10
Last pre-intervention period (T0) 5
Matching PS Nearest neighbor
MIP Matching tolerance .05 SD
Number of simulations 1,000
  • Estimate compared to sample ATT (different for matching)
  • When matching with post-treat covariates compared with direct effect τ

Summary of results

  • For time-invariant covariates, matching actually helps.
  • For time-varying covariates, matching on pre-intervention covariates can improve estimation unless they diverge post.

    • Can try to bind effects.
  • Autocorrelation for time-varying covariates also plays an important role:

    • If they come from different distributions, high-autocorrelation is better.

Application

Preferential Voucher Scheme in Chile

  • Universal flat voucher scheme 2008 Universal + preferential voucher scheme

  • Preferential voucher scheme:

    • Targeted to bottom 40% of vulnerable students

    • Additional 50% of voucher per student

    • Additional money for concentration of SEP students.

Preferential Voucher Scheme in Chile

  • Universal flat voucher scheme 2008 Universal + preferential voucher scheme

  • Preferential voucher scheme:

    • Targeted to bottom 40% of vulnerable students

    • Additional 50% of voucher per student

    • Additional money for concentration of SEP students.

      Students:
      - Verify SEP status
      - Attend a SEP school

Schools:
- Opt-into the policy
- No selection, no fees
- Resources ~ performance

Impact of the SEP policy

  • Positive impact on test scores for lower-income students (Aguirre, 2019; Nielson, 2016)

  • Design could have increased socioeconomic segregation

    • Incentives for concentration of SEP students
  • Key decision variables: Performance, current SEP students, competition, add-on fees.

  • Diff-in-diff (w.r.t. 2007) for SEP and non-SEP schools:

    • Only for private-subsidized schools

    • Matching between 2005-2007 --> Effect estimated for 2008-2011

    • Outcome: Average students' household income

Before Matching

diagram

  • No (pre) parallel trend

  • Covariates evolve differently in the pre-intervention period

[Pre] parallel trends

diagram

diagram

After Matching

diagram

  • MIP Matching:

    • Mean balance (0.05 SD): Rural, enrollment, number of schools in county, charges add-on fees

    • Fine balance: Test scores, monthly average voucher.

  • 6% increase in the income gap between SEP and non-SEP schools

Let's wrap it up

Conclusions

  • Matching can be an important tool to address violations in PTA.

  • Relevant to think whether groups come from the same or different populations.

  • Serial correlation also plays an important role: Don't match on random noise.

Match well and match smart!

A Difference-in-Differences Approach
using Mixed-Integer Programming Matching

Magdalena Bennett



www.magdalenabennett.com

Additional Slides

Results: Time-invariant covariates

Results: Time-varying covariates

Other simulations

  • Test regression to the mean under no effect:

    • Vary autocorrelation of Xi(t) (low vs. high)
    • X0(t) and X1(t) come from the same or different distributions.

Diff-in-Diff as an identification strategy

Paused

Help

Keyboard shortcuts

, , Pg Up, k Go to previous slide
, , Pg Dn, Space, j Go to next slide
Home Go to first slide
End Go to last slide
Number + Return Go to specific slide
b / m / f Toggle blackout / mirrored / fullscreen mode
c Clone slideshow
p Toggle presenter mode
t Restart the presentation timer
?, h Toggle this help
sToggle scribble toolbox
Esc Back to slideshow