Aggregated multi-dimensional indices are causally mismeasured when they include causally irrelevant components.

Evidence

The Causal Powers Guideline leads naturally to what one might call “causal mismeasurement.” Including a potentially irrelevant—because it has no causal influence—dimension in a concept means that the values on that dimension will influence the final numeric value because the multiple dimensions must be aggregated in some fashion to get the final value. Thus each dimension contributes, though perhaps not for every observation, to the final value. If the dimension is causally irrelevant this means that the final value will be causally off because of this irrelevant information. So while there may not be any mismeasurement in the usual descriptive sense, in the causal sense there is. — Gary Goertz, Social Science Concepts and Measurement, 519

Categorization

• DEFINE: Introduces ‘causal mismeasurement’ as a distinct error from descriptive mismeasurement — a measurement can be numerically correct yet causally wrong.
• XREF: Connects to composite-index critique in development metrics work (GDP, HDI, freedom indices) where weighting choices silently encode causal theories.