Using Generalizability Theory to Explore the Trustworthiness of Survey Data From an International Development Evaluation

• In Event: 72.066 - Poster Session 16
  In Poster Session: 72.066-8 - Division D Section 2 Poster Session

Abstract

Recent global initiatives have shifted the focus of accountability of international development organizations from immediate outputs to long-term outcomes of funded programs. This paradigm shift requires the use of the formerly under-utilized method of impact evaluation which seeks to establish a link between desired outcomes of a program, or intervention, and said program or intervention. Establishing a link between program efforts and outcomes requires the collection and evaluation of both factual and counterfactual evidence in a randomized controlled trial (RCT) design. Data from an ongoing evaluation in the Democratic Republic of the Congo is analyzed using Generalizability theory to provide some insight into the effects two different adaptation methods of a survey administered by enumerators.

Authors

• Fen Fan, University of Massachusetts - Amherst

• Louise M. Bahry, Pearson VUE

• Jennifer Randall, University of Massachusetts

• Lisa A. Keller, University of Massachusetts - Amherst