Comparing Performance of Methods to Deal with Differential Attrition in Lottery Based EvaluationsReportar como inadecuado

Comparing Performance of Methods to Deal with Differential Attrition in Lottery Based Evaluations - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Society for Research on Educational Effectiveness

The purpose of this study is to study the performance of different methods (inverse probability weighting and estimation of informative bounds) to control for differential attrition by comparing the results of different methods using two datasets: an original dataset from Portland Public Schools (PPS) subject to high rates of differential attrition, and the expanded PPS and state level dataset that does not suffer as much from differential attrition. The main research questions are: (1) Do various methods (inverse probability weighting or estimation of informative bounds) adequately compensate for differential attrition in a random assignment evaluation; and (2) How do various assumptions within these methods affect the results? This study utilizes two datasets which will be compared using various methods: (1) PPS school district data: this data set experienced high levels of differential attrition. Attrition in the control group was about 24 percentage points higher than attrition in the treatment group; and (2) PPS school district data supplemented with Oregon Department of Education (ODE) State level data. This will serve as the benchmark with which to compare the district-level data that experienced more differential attrition. Once the data was supplemented, differential attrition was reduced to only about 6 percentage points.

Descriptors: Data Analysis, Student Attrition, Evaluation Methods, Evaluation Research, Probability, Weighted Scores, Randomized Controlled Trials, Control Groups, Experimental Groups, School Districts, School Statistics, Computation, Comparative Analysis, Scoring Rubrics, State Standards, Benchmarking, Statistical Studies, Predictor Variables

Society for Research on Educational Effectiveness. 2040 Sheridan Road, Evanston, IL 60208. Tel: 202-495-0920; Fax: 202-640-4401; e-mail: inquiries[at]; Web site:

Autor: Zamarro, Gema; Anderson, Kaitlin; Steele, Jennifer; Miller, Trey


Documentos relacionados