Measuring the Unmeasurable? Systematic Evidence on Scale Transformations in Subjective Survey Data

Abstract

Ordered response scales are ubiquitous in economics, but their interpretation rests on an untested assumption: that numerical labels reflect equal psychological intervals. We develop a framework to quantify how relaxing this assumption affects empirical results. Using new experimental evidence, we show that scale use is only mildly non-linear. Replicating over 40,000 estimates from more than 80 papers, we find that coefficient signs and significance are largely robust, but relative magnitudes are not. Even modest non-linearities generate substantial variation in implied trade-offs.