TY  - RPRT
        AU  - Millimet, Daniel L.
AU  - Paloyo, Alfredo R.
        TI  - On the (Mis)Use of Composite Indices: with Applications in Political Economy
        PY  - 2026/Mar/
        PB  - Institute of Labor Economics (IZA)
        CY  - Bonn
        T2  - IZA Discussion Paper
        IS  - 18454
        UR  - https://www.iza.org/index.php/publications/dp18454
        AB  - Empirical researchers often replace latent constructs with composite indices, treating this as a neutral data-processing step. We prove this is a consequential identification choice. Our (near) impossibility theorem demonstrates that no linear index can guarantee consistent estimates of all parameters in multiple regressions. We show that proxy indices induce residual confounding, while popular weighting schemes introduce nonclassical measurement error with method-dependent biases. Using simulations and 2024 U.S. election data, we reveal that substantive conclusions are often artifacts of the chosen index. We argue that measurement models require the same formal scrutiny as other identification strategies.
        KW  - latent variables
KW  - composite indices
KW  - measurement models
KW  - errors-in-variables
KW  - proxy variables
KW  - political economy
KW  - community health
        ER  -