The presentation will revisit some of the conceptual and statistical foundations of psychometric measurement theory and factor analysis, specifically addressing the questions: (i) What happens to “factors” when they causally affect one another?, (ii) Is an underlying univariate latent variable a reasonable model for psycho-social constructs?, (iii) What are the testable empirical implications of such a model? and (iv) What alternative interpretations of analyses with constructed measures might be possible?
The presentation will be based upon the following three preprints:
- VanderWeele, T.J. and Batty, C.J.K. (2020). On the dimensional indeterminacy of one-wave factor analysis under causal effects. Technical Report.
- VanderWeele, T.J. and Vansteelandt, S. (2020). A statistical test to reject the structural interpretation of a latent factor model. Technical Report.
- VanderWeele, T.J. (2020). Causal inference and constructed measures: towards a new model of measurement for psychosocial constructs. Technical Report.