Goldstein
Goldstein
Goldstein
• Easy to understand
(for instance: poverty incidence is easier to understand and to
communicate than poverty depth)
• Reliable
(for instance: scientific, objective indicators are more reliable
than indicators which depend on the interpretation of the user.
This is related to the above discussion on “manipulation”)
Indicators: What qualities?
But more than anything else….
• Disadvantages:
– Ethical issues, political constraints
– Internal validity (exogeneity): people might not comply with the
assignment (selective non-compliance)
– Unable to estimate entry effect
– External validity (generalizability): usually run controlled
experiment on a pilot, small scale. Difficult to extrapolate the
results to a larger population.
Randomization & decentralization
• Randomize the roll out of reforms…
– Political issues
– Implementation issues
• Randomize phase in (have to work fast)
• Randomize sub-components:
– e.g. Randomize TA, or the phase-in of TA
• Randomize different packages (e.g. some units
get TA and computers, some units get only TA)
…but this answers a different question
• Randomize who rules…India panchayats
2. Matching
• Match participants with non-participants from a
larger survey
• Counterfactual: matched comparison group
Y0
Y0
• Advantages:
– Does not require the exogeneity assumption of matching
• Disadvantages:
– The estimated effect is local: IV identifies the effect of the
program only for the sub-population of those induced to take-up
the program by the instrument
– Therefore different instruments identify different parameters. End
up with different magnitudes of the estimated effects
– Validity of the instrument can be questioned, cannot be tested.
IV and Decentralization
• Random encouragement…If we have a
program where local government has to
enroll, we randomly allocate
encouragement – this is “exogenous” and
can serve as an instrument
• Generally tough – requires creativity…
5.Regression discontinuity design
• Exploit the rule generating assignment into a program
given to individuals only above a given threshold –
Assume that discontinuity in participation but not in
counterfactual outcomes
• Counterfactual: individuals just below the cut-off who did
not participate
• Advantages:
– Identification built in the program design
– Delivers marginal gains from the program around the
eligibility cut-off point. Important for program expansion
• Disadvantages:
– Threshold has to be applied in practice, and individuals
should not be able manipulate the score used in the
program to become eligible.
Figure 1: Kernel Densities of Discriminant Scores and Threshold points by region
Density
Density
3.9e-06 2.8e-06 0
759 753 751
Discriminant Score Discriminant Score Discriminant Score
Region 3 Region 4 Region 5
.004142 .004625 .003639
Density
Density
Density
5.5e-06 8.0e-06 4.5e-06
752 571 691
Discriminant Score Discriminant Score Discriminant Score
Region 6 Region 12 Region 27
.002937
Density
.000015
757
Discriminant Score
Region 28
Example from Buddelmeyer and
Skoufias, 2005
RDD in decentralization
• Need a program with a specific rule as to
which units are eligible
• e.g. only local government units below a
certain poverty threshold get power over a
certain set of expenditures
• Need lots of units around the cut off
Resources for doing impact
evaluations
• Website: type impactevaluation into your
browser
– Range of training materials
– Database of completed evaluations
– Roster of consultants
• Clinics - on demand, customized support
• Training