A Note on the Usefulness of the Behavioural Rasch Selection Model for Causal Inference in the Social Sciences

2016 Joint IMEKO TC1-TC7-TC13 Symposium: Metrology Across the Sciences: Wishful Thinking?

Rabbitt, Matthew P.^1

Economic Research Service, U.S. Department of Agriculture, 355 E Street, SW, Washington

DC

20024-3221, United States^1

关键词: Causal inferences;    Causal relationships;    Measurement model;    Monte Carlo experiments;    Selection model;    Social scientists;    Survey data;    Treatment effects;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/772/1/012048/pdf
DOI  :  10.1088/1742-6596/772/1/012048

来源: IOP

【 摘 要 】

Social scientists are often interested in examining causal relationships where the outcome of interest is represented by an intangible concept, such as an individual's well-being or ability. Estimating causal relationships in this scenario is particularly challenging because the social scientist must rely on measurement models to measure individual's properties or attributes and then address issues related to survey data, such as omitted variables. In this paper, the usefulness of the recently proposed behavioural Rasch selection model is explored using a series of Monte Carlo experiments. The behavioural Rasch selection model is particularly useful for these types of applications because it is capable of estimating the causal effect of a binary treatment effect on an outcome that is represented by an intangible concept using cross-sectional data. Other methodology typically relies of summary measures from measurement models that require additional assumptions, some of which make these approaches less efficient. Recommendations for application of the behavioural Rasch selection model are made based on results from the Monte Carlo experiments.