×

Misreported schooling, multiple measures and returns to educational qualifications. (English) Zbl 1311.62198

Summary: We consider the identification and estimation of the average wage return to attaining educational qualifications when attainment is potentially measured with error. By exploiting two independent measures of qualifications, we identify the extent of misclassification in administrative and self-reported data on educational attainment. The availability of multiple self-reported educational measures additionally allows us to identify the temporal patterns of individual misreporting errors across survey waves. We provide the first reliable estimate of a highly policy relevant parameter for the UK, namely the return from attaining any academic qualification compared to leaving school at the minimum age without any formal qualification. We identify returns to qualifications under two alternative settings: a strong ignorability assumption and an exclusion restriction. All these results are obtained by casting the identification problem in terms of a mixture model, and using a semi-parametric estimation approach based on balancing scores, which allows for arbitrarily heterogeneous individual returns.

MSC:

62P25 Applications of statistics to social sciences

References:

[1] Aigner, D., Regression with a binary independent variable subject to errors of observation, J. Econometrics, 1, 49-60 (1973) · Zbl 0279.62016
[2] Almlund, M.; Duckworth, A.; Heckman, J.; Kautz, T., Personality psychology and economics, (Hanushek, S. M.E.; Woessman, L., Handbook of the Economics of Education, vol. 4 (2011), Elsevier: Elsevier Amsterdam), 1-181
[4] Battistin, E.; Sianesi, B., Misclassified treatment status and treatment effects: an application to returns to education in the UK, Rev. Econ. Stat., 93, 2, 495-509 (2011)
[5] Black, D.; Berger, M.; Scott, F., Bounding parameter estimates with non-classical measurement error, J. Amer. Statist. Assoc., 95, 451, 739-748 (2000)
[6] Black, D.; Sanders, S.; Taylor, L., Measurement of higher education in the census and current population survey, J. Amer. Statist. Assoc., 98, 463, 545-554 (2003)
[7] Blundell, R.; Dearden, L.; Sianesi, B., Measuring the returns to education, (What’s the Good of Education? The Economics of Education in the UK (2005), Princeton University Press), 117-145
[8] Blundell, R.; Dearden, L.; Sianesi, B., Evaluating the effect of education on earnings: models, methods and results from the national child development survey, J. R. Stat. Soc. Ser. A, 168, 3, 473-512 (2005) · Zbl 1120.62109
[9] Borghans, L.; Duckworth, A.; Heckman, J. J.; ter Weel, B., The economics and psychology of personality traits, J. Hum. Resour., 43, 4, 972-1059 (2008)
[10] Bound, J.; Brown, C.; Mathiowetz, N., Measurement error in survey data, (Heckman, J. J.; Leamer, E., Handbook of Econometrics. Vol. 5 (2001), North-Holland: North-Holland Amsterdam), 3705-3843
[11] Chen, X.; Hong, H.; Nekipelov, D., Nonlinear models of measurement errors, J. Econ. Lit., 49, 4, 901-937 (2011)
[12] Chevalier, A.; Harmon, C.; Walker, I.; Zhu, Y., Does education raise productivity, or just reflect it?, Econ. J., 114, 499, 499-517 (2004)
[14] Dearden, L.; McIntosh, S.; Myck, M.; Vignoles, A., The returns to academic and vocational qualifications in britain, Bull. Econ. Res., 54, 249-274 (2002)
[17] Di Nardo, J.; Lee, D. S., Program evaluation and research designs, (Handbook of Labor Economics, Vol. 4, Part A (2011)), 463-536, (Chapter 5)
[18] Everitt, B. S.; Hand, D. J., Finite Mixture Distributions (1981), Chapman and Hall: Chapman and Hall London · Zbl 0466.62018
[19] Fisher, R. A., The Design of Experiments (1935), Oliver & Boyd: Oliver & Boyd Edinburgh
[20] Fleiss, J. L., Measuring nominal scale agreement among many raters, Psychol. Bull., 76, 5, 378-382 (1971)
[21] Heckman, J. J.; Honore, B. E., The empirical content of the Roy model, Econometrica, 58, 5, 1121-1149 (1990)
[22] Heckman, J. J.; Lalonde, R.; Smith, J., The economics and econometrics of active labor market programs, (Ashenfelter, A.; Card, D., Handbook of Labor Economics, vol. 3 (1999), Elsevier Science: Elsevier Science Amsterdam)
[23] Heckman, J. J.; Pinto, R.; Savelyev, P., Understanding the mechanisms through which an influential early childhood program boosted adult outcomes, Amer. Econ. Rev., 103, 6, 2052-2086 (2013)
[24] Hu, Y., Identification and estimation of nonlinear models with misclassification error using instrumental variables: a general solution, J. Econometrics, 144, 1, 27-61 (2008) · Zbl 1418.62474
[25] Hui, S. L.; Walter, S. D., Estimating the error rates of diagnostic tests, Biometrics, 36, 1, 167-171 (1980) · Zbl 0436.62093
[26] Imbens, G. W., The role of the propensity score in estimating dose-response functions, Biometrika, 87, 3, 706-710 (2000) · Zbl 1120.62334
[27] Imbens, G. W., Semiparametric estimation of average treatment effects under exogeneity: a review, Rev. Econ. Stat., 86, 4-29 (2004)
[28] Imbens, G. W.; Angrist, J., Identification and estimation of local average treatment effects, Econometrica, 62, 2, 467-475 (1994) · Zbl 0800.90648
[29] Imbens, G. W.; Rubin, D. B., Estimating outcome distributions for compliers in instrumental variables models, Rev. Econom. Stud., 64, 555-574 (1997) · Zbl 0887.90041
[32] Kreider, B.; Pepper, J. V., Disability and employment: reevaluating the evidence in light of reporting errors, J. Amer. Statist. Assoc., 102, 478, 432-441 (2007) · Zbl 1134.62397
[33] Kreider, B.; Pepper, J. V.; Gundersen, C.; Jollife, D., Identifying the effects of snap (food stamps) on child health outcomes when participation is endogenous and misreported, J. Amer. Statist. Assoc., 107, 499, 958-975 (2012) · Zbl 1395.62342
[34] Landis, J. R.; Koch, G. G., The measurement of observer agreement for categorical data, Biometrics, 33, 159-174 (1977) · Zbl 0351.62039
[35] Lechner, M., Identification and estimation of causal effects of multiple treatments under the conditional independence assumption, (Lechner, M.; Pfeiffer, F., Econometric Evaluation of Labour Market Policies (2001), Physica: Physica Heidelberg), 43-58
[36] Lewbel, A., Estimation of average treatment effects with misclassification, Econometrica, 75, 2, 537-551 (2007) · Zbl 1132.91593
[37] Mahajan, A., Identification and estimation of regression models with misclassification, Econometrica, 74, 3, 631-665 (2006) · Zbl 1128.62050
[38] Manski, C. F.; Pepper, J. V., Monotone instrumental variables: with an application to the returns to schooling, Econometrica, 68, 4, 997-1010 (2000) · Zbl 1016.62133
[39] McIntosh, S., Further analysis of the returns to academic and vocational qualifications, Oxf. Bull. Econ. Stat., 68, 2, 225-251 (2006)
[40] Mellow, W.; Sider, H., Accuracy of response in labor market surveys: evidence and implications, J. Labor Econom., 1, 4, 331-344 (1983)
[41] Molinari, F., Partial identification of probability distributions with misclassified data, J. Econometrics, 144, 1, 81-117 (2008) · Zbl 1418.62522
[42] Neyman, J., Statistical problems in agricultural experimentation, Suppl. J. R. Stat. Soc., 2, 107-180 (1935), (with co-operation by Iwaszkiewicz, K., and Kolodziejczyk, S.) · JFM 63.1103.02
[43] Quandt, R., Methods for estimating switching regressions, J. Amer. Statist. Assoc., 67, 306-310 (1972) · Zbl 0237.62047
[44] Roy, A., Some thoughts on the distribution of earnings, Oxf. Econ. Papers, 3, 135-146 (1951)
[45] Rubin, D. B., Estimating causal effects of treatments in randomised and non-randomised studies, J. Educ. Psychol., 66, 688-701 (1974)
[46] Rubin, D. B., Discussion of randomisation analysis of experimental data in the Fisher randomisation test’ by Basu, J. Amer. Statist. Assoc., 75, 591-593 (1980)
[47] Seber, G. A.F., A Matrix Handbook for Statisticians (2008), Wiley: Wiley New Jersey · Zbl 1143.15001
[48] Yakowitz, S. J.; Spragins, J. D., On the identifiability of finite mixtures, Ann. Math. Stat., 39, 209-214 (1968) · Zbl 0155.25703
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.