Presentation is loading. Please wait.

Presentation is loading. Please wait.

Prof. (FH) Dr. Alexandra Caspari Rigorous Impact Evaluation What It Is About and How It Can Be.

Similar presentations


Presentation on theme: "Prof. (FH) Dr. Alexandra Caspari Rigorous Impact Evaluation What It Is About and How It Can Be."— Presentation transcript:

1 Prof. (FH) Dr. Alexandra Caspari caspari@fb4.fh-frankfurt.de www.fh-frankfurt.de/caspari Rigorous Impact Evaluation What It Is About and How It Can Be Done In Practice Alexandra Caspari, Frankfurt/Main Germany Conference »Perspectives on Impact Evaluation: Approaches to Assessing Development Effectiveness« 31 st March – 2 nd April 2009, Cairo

2 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 1 University of Applied Sciences Historical Review – The Evaluation Gap  MDGs (2000), ‘Paris Declaration on Aid Effectiveness’ (2005), and ‘Agenda for Action’ (Accra, 2008):  Increasing attention to Impact Evaluations  Lack of knowledge about effectiveness of projects and programs  2006: Report “When will we ever learn?” of the CGD ‘Evaluation Gap Working Group’  gap in quantity and quality of impact evaluations: -too few impact evaluations are being carried out and -those conducted often unable to properly assess impact because of methodological shortcomings  Recommendation: ‘Collective Action’  International Initiatives (NONIE, 3IE, …)

3 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 2 University of Applied Sciences What is Impact Evaluation?  OECD/DAC (2002): “positive and negative, primary and secondary long-term effects produced by a development intervention, directly or indirectly, intended or unintended”  emphasises on ‘produced by’: -measures impact with clear causation (causal attribution) -considers the counterfactual, i.e. the question “What difference did this program make?” “What would have happened without the intervention?” Rigorous Impact Evaluation (RIE):  Distinction against more “usual evaluations” by adding “rigorous”  focus on clear causation  use of adequate methods (to meet methodological shortcomings)  most important point: selection of the evaluation design to consider the counterfactual

4 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 3 University of Applied Sciences The Counterfactual  Causal effect: An actual effect δ i caused by a treatment T (a program) is the difference between the outcome Y i1 under a treatment T (T=1), i.e. program participant, minus the alternative outcome Y i0 that would have happened without the treatment T (T=0), i.e. non-participant :  Impact is not directly observable: -one can observe any given individual either as a treated person (participant) or untreated person (non-participant) but not both states -if individual i is participating in a program (T=1), then the outcome Y i0 is unobservable -this unobservable outcome Y i0 is called counterfactual  Analyzing the difference between the observed outcome and the unobserved potential outcome by choosing the best evaluation design

5 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 4 University of Applied Sciences Considering the Counterfactual  often used non-experimental designs: ● : observation, P: participants (treated), t: time (first, second observation), X: project intervention one-group pre-test post-test design (a) time t2t2 t1t1 P measured impact impact indicator  measured impact =  the counterfactual is not considered!  with non-experimental designs causal attribution is not possible!

6 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 5 University of Applied Sciences Considering the Counterfactual  necessary: experimental or quasi-experimental designs  adequate comparison group (‘with-and without comparison’)  „Real“ Experiments / Randomized Controlled Trials (RCTs): (Laboratory)Experiments: -random assignment of individuals to treatment (P) and control group (C)  groups differ solely due to chance -treatment and conditions are known/checkable Field experiments: -take place in real-world settings -anyhow treatment and control groups are assigned at random  Quasi-Experiments: -no random assignment -has a source of randomization that is “as if” randomly assigned -control group is often reconstructed ex-post

7 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 6 University of Applied Sciences Considering the Counterfactual ● : observation, P: participants (treaded), C: control group (non-treated), D: difference, t: time (first, second observation), X: project intervention over- estimated impact one-group pre-test post-test design (a) time t2t2 t1t1 P measured impact impact indicator static group comparison (4) time impact indicator t2t2 t1t1 C P measured impact = D t2 (single difference) time impact indicator t2t2 t1t1 C P D t1 pre-test post-test control group design (1)/(2) (double difference) measured impact = D t2 – D t1 D t2

8 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 7 University of Applied Sciences Approaches to Impact Evaluation  appropriate impact evaluation designs are often reject as unnecessarily sophisticated or because of ethical concerns  various realistic ways in which quasi-experimental designs can be introduced in an ethically and politically acceptable manner: -Matching on Observables -Regression Discontinuity -Propensity Score Matching (PSM) -Pipeline Approach -Multiple Comparison Group Design

9 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 8 University of Applied Sciences Possible Approaches in Practice  Matching on Observables: -characteristics (access tor services, economic level, type of housing, etc.) on which the comparison group should match the program group (individuals, households or areas) are identified carefully -often easily observable or identifiable characteristics -unobservable differences has to be kept in mind -control group is build out of those individuals, households or areas which match best -quasi-experimental design “pretest-posttest-comparison with post- test non-equivalent control group” (3) or at least “static group comparison” (4) is possible  single-difference (SD) possible

10 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 9 University of Applied Sciences Possible Approaches in Practice  Regression Discontinuity: -if a program is assigned using a clear threshold for eligibility comprised for one ore more criteria (age, income less than…) -control group is built out of those just above the threshold and hence not eligible for the program -those individuals will have comparable characteristics -quasi-experimental design “pre-test post-test non-equivalent control group design” (2) possible!  double-difference (DD) possible!

11 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 10 University of Applied Sciences Possible Approaches in Practice  Pipeline Approach: -if large programs (housing or community infrastructure, immunization, …) are introduced in phases over several years -when there are no major differences between the characteristics of families, communities scheduled for each phase and -when there is no selection criteria for participants of the first phase (the poorest families, communities, …)  participants of phase 2 & 3 = control group for participants phase 1  quasi-experimental design “pre-test post-test non-equivalent control group design” (2) possible!  double-difference (DD) possible

12 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 11 University of Applied Sciences Important Remarks  The international discussion about RIE refers just to a small aspect of evaluation: the causal attribution of impact  Impact is measured at the level of target groups/participants  because target groups are typically large, for this evaluation step quantitative methods are necessary (representativeness vs. profundity)  other evaluation methods are not condemned!  causal attribution is necessary but not sufficient  ‘black box’ remains: why does a program have impact (or does not)  comprehensive meaningful and reliable impact evaluations need the use of mixed method, i.e. use of quantitative and qualitative methods

13 Fachhochschule Frankfurt am Main – Alexandra Caspari, 31/03/2009, CairoSlide 12 University of Applied Sciences  http://www.fh-frankfurt.de/de/.media/~caspari/2008bmzwpwirkungsevaluation.pdf Reference: Caspari, Alexandra/Barbu, Ragnhild (2008): Wirkungsevaluierungen Zum Stand der internationalen Diskussion und dessen Relevanz für die Evaluierung der deutschen Entwicklungszusammenarbeit


Download ppt "Prof. (FH) Dr. Alexandra Caspari Rigorous Impact Evaluation What It Is About and How It Can Be."

Similar presentations


Ads by Google