Changing Wage Effects of Educational Mismatch in China: Evidence from Threshold IV–Selection Models

This study re-examines the wage effects of educational mismatch in China by jointly addressing sample selection, endogeneity, and nonlinear career dynamics within a unified econometric framework. While educational mismatch has been widely analyzed, little is known about how its wage effects evolve across the career cycle or how these dynamics have shifted over time. Using harmonized waves of the China Family Panel Studies (CFPS) for 2010 and 2020, we extend the Duncan–Hoffman model by embedding a sample-selection-corrected threshold regression estimated via instrumental variables. This approach allows us to identify experience thresholds at which the returns to overeducation and undereducation shift regimes. Our findings uncover strong nonlinearities. In 2010, overeducated workers experienced sizable wage penalties throughout most of their careers, with only modest attenuation beyond the threshold, while undereducated workers received early-career wage premiums that diminished or reversed at higher experience levels. By 2020, experience thresholds decreased markedly, mismatch penalties attenuated more rapidly, and the wage effects of overeducation became more homogeneous across gender groups. These results suggest that China’s evolving labor market has reduced the persistence and heterogeneity of mismatch-related wage disparities. JEL: I26, J24, J31, C34