SMABS 2004 Jena University
SMABS 2004 Home Organization About Jena Sponsors Links Imprint / Contact SMABS Home

European Association of Methodology

Department of methodology and evaluation research

Jena University

Contributions: Abstract

Analysis of individual and average causal effects and threats to validity

Salvador Chacn-Moscoso Susana Sanduvete Chaves
University of Sevilla
Spain
F. Pablo Holgado-Tello
UNED, Madrid
Spain

In this paper we study the relationship between the Campbellian approach to validity threats and the approach of Rubin to the analysis of (individual and average) causal effects. First we present a brief description of the conceptual bases of validity and main threats to the various kinds of validity (Shadish, Cook and Campbell, 2002) and we also analyze the main concepts of statistical inference for causal effects. Second, based on a model for analyzing individual causal effects (Steyer, 2002) we discuss what the Campbellian tradition adds to the methods of analyzing causal effects. Specifically, using SEM methodology, we study the threats to validity in Steyer's model for the analysis of individual causal effects. This includes the issue of external validity. We also propose some possible extensions to the design and model.