Methods for Synthesizing Regression Models: The Case of Education Production Functions

Principal Investigator: 
Project Overview
Background & Purpose: 

The purpose of the study is to develop methods for synthesizing studies that use regression models to examine the relationships between an outcome and a series of predictors. We are studying these methods using research on education production functions, where the goal is to estimate the relationship between per-pupil expenditures and achievement outcomes.


This is a comparative project designed to generate synthesis [meta-analysis] evidence. This project involves conducting a comprehensive review of the educational production function literature.

Research Design: 

We are developing techniques for combining studies that use regression models. We are examining the use of missing data techniques as applied to this context to synthesize studies that propose different education production function models.


This project has not yet generated findings.

Publications & Presentations: 

Pigott, T. D. & Wu, M.-J. (2008, May). Issues in meta-analysis for results of regression. Annual Meeting of the Campbell Collaboration, Vancouver, B.C.

Pigott, T. D. & Wu, M.-J. (2007, July). Meta-analysis methods for synthesizing results of regression. Annual Meeting of the Society for Research Synthesis, Chicago, IL.

Other Products: 

This project expects to generate new methods for meta-analysis.