ANALYZING EDUCATIONAL MISMATCH IN TURKISH LABOR MARKET ADDRESSING DIFFERENT ESTIMATION METHODS

Date

2025-4-07

Author

Erdem Karahanoğlu, Gülbin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

45
views

39
downloads

Cite This

This dissertation provides a comprehensive analysis of educational mismatch in Turkish labor market and its impact on wages by addressing key econometric challenges through advanced estimation methods. The research first corrects for non-random selection into employment using an augmented Heckman selection model, then tackles the joint endogeneity inherent in both education and educational mismatch with instrumental variable (IV) techniques and finally captures the variation in wage effects across the distribution using unconditional quantile regression. The empirical findings reveal that both selection bias and endogeneities are addressed both educational attainment and mismatch exert much higher effects on earnings than conventional estimates suggest. The IV results indicate a substantially higher return to schooling and far greater wage penalties for mismatch. Overeducated employees are found to earn markedly less than comparable well-matched peers, and undereducated employees suffer a considerably larger wage deficit than previously estimated. Combining IV with selection correction yields the largest effects confirming that standard models severely understate the true costs of mismatch. Finally, penalties derived from educational mismatch vary markedly across the wage distribution: lower-wage workers suffer the largest relative wage losses when overeducated or undereducated, while higher-wage mismatched workers experience much smaller earnings penalties and may even benefit slight wage premiums in certain cases. Overall, the dissertation’s results demonstrate that standard methods severely underestimate the wage penalties associated with educational mismatch. Using multi-faceted approaches provides more accurate and robust results.

Subject Keywords

Educational Mismatch, Wage Inequality, Selection Bias, Instrumental Variables, Unconditional Quantile Regression

URI

https://hdl.handle.net/11511/114069

Collections

Graduate School of Social Sciences, Thesis