Journal of the Iranian Statistical Society

Instrumental Variables Regression with Measurement Errors and Multicollinearity in Instruments

Authors

1 Department of Statistics, Faculty of Mathematics and Computer, Shahid Bahonar University of Kerman, Kerman, Iran.

2 epartment of Biostatistics and Data Science, School of Public Health, University of Texas Health Science Center at Houston (UTHealth), Houston, Texas, USA.

3 Department of Statistics, University of Birjand, Birjand, Iran.

10.52547/jirss.19.2.15

Abstract

In this paper we obtain a consistent estimator when there exist some measurement errors and multicollinearity in the instrumental variables in a two stage least square estimation of parameters. We investigate the asymptotic distribution of the proposed estimator and discuss its properties using some theoretical proofs and a simulation study. A real numerical application is also provided for more illustration.

Keywords

  1. Akdeniz F., Roozbeh M,. (2017) Efficiency of the generalized-difference-based weighted mixed almost unbiased two-parameter estimator in partially linear model. Communica- tions in Statistics - Theory and Methods, 46(24), 12259-12280. Arashi M., Tabatabaey S. M. M. and Hassanzadeh Bashtian M. (2014). Shrinkage ridge estimators in linear regression, Communication in Statistics - Simulation and Com- putation, 43, 871-904. Bowden R. and Turkington D. (1984). Instrumental variables. Cambridge University Press, NY. Burgess S., Small D. S. and Thompson S. G. (2017). A review of instrumental variable estimators for Mendelian randomization. Statistical Methods in Medical Research. 26(5), 2333-2355. Burgess S. and Dylan S. (2016). Predicting the Direction of Causal Effect Based on an Instrumental Variable Analysis: A Cautionary Tale. J. Causal Infer. 4(1), 49-59. Cao C. Z., Lin J. G., Shi J. Q., Wang W. and Zhang X. Y. (2015). Multivariate measurement error models for replicated data under heavy-tailed distributions. Chemo- metrics, 8, 457-466. Carrasco M. (2012). A regularization approach to the many instruments problem. Journal of Econometrics, 170(2), 383-398. Carrasco M. and G. Tchuente (2015). Regularized LIML for many instruments. Jour- nal of Econometrics, 186(2), 427-442. Carroll R., Ruppert J. D., Stefanski L. A. and Crainiceanu C. M. (2006). Measurement Error in Nonlinear Models: A Modern Perspective, CRC Press, Boca Raton, Fla, 2nd edition, pp. 485. Chan L.K. and Mak T.K. (1979). On the maximum likelihood estimation of a linear structural relationship when the intercept is known. J. Multivar. Anal. 9, 304-313. Devanarayana V. and Stefanski L. A. (2002). Empirical Simulation Extrapolation for Measurement Error Models With Replicate Measurements, Statis tics and Probability Letters, 59, 219-225. Didelez V. and Sheehan N. A. (2007). Mendelian randomization as an instrumental variable approach to causal inference. Stat Meth Med Res, 16, 309-330. Ebbes P. (2004). Latent Instrumental Variables - A New Approach to Solve for En- dogeneity. Ph.D.thesis, University of Groningen Economics and Business. Golub G. H., Heath M. and Wahba G. (1979). Generalized cross-validation as a method for choosing a good ridge parameter. Technometrics. 21, 215-223. Lawlor, D. A., Harbord R. M., Sterne J. A.,Timpson N. and Smith G. D. (2008). Mendelian randomization: using genes as instruments for making causal inferences in epidemiology. Statistics in Medicine. 27(8), 1133-1163. Liu X., Q., and , Jiang H., Y. (2012). Optimal generalized ridge estimator under the generalized cross-validation criterion in linear regression. Linear Algebra and its Applications. 436 (5), 1238-1245. Fallah R., Arashi M. and Tabatabaey S. M. M. (2017). On the ridge regression es- timator with sub- space restriction, Communication in Statistics Theory and Methods, 46(23), 11854-11865. Ghapani F., Babadi B. (2016). A New Ridge Estimator in Linear Measurement Error Model with Stochastic Linear Restrictions. JIRSS , Vol. 15, No. 2, pp 87-103. Hausman J.A. (1978). Specification tests in econometrics. Econometrica, 46, 1251- 1271. Hansen C. and Kozbur D. (2014). Instrumental Variables Estimation with Many Weak Instruments Using Regularized JIVE. Journal of Econometrics. 182(2), 290-308. Harris M.H., Gold, D.R., Rifas-Shiman S.L., Melly S.J., Zanobetti,A., Coul B.A. Schwartz J.D., Gryparis A., Kloog I., Koutrakis P. (2016). Prenatal and childhood traffic- related air pollution exposure and childhood executive function and behavior. Neurotox- icol. Teratol. 57, 6070 Horel A. E. and Kennard R. W. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12, 55- 83. Isogawa, Y. (1985). Estimating a multivariate linear structural relationship with repli- cation. J. R. Statist. Soc. B, 47, 211-215. Lachos B.G. and Bolfarine, H. (2016). Heavy tailed calibration model with Berk- son measurement errors for replicated data. Chemometrics and Intelligent Laboratory systems, 156, 21-35. Lousdal M., Lise. (2018). An introduction to instrumental variable assumptions, validation and estimation. Emerging themes in epidemiology. 15(1), 1-7. Nawarathna, L.S. and Choudhary, P. K. (2015). A Heteroscedastic Measurement Error Model for Method Comparison Data With Replicate Measurements. Statistics in Medicine, 34(7), 1242-1258. Okbay A. et al. (2016). Genome-wide association study identifies 74 loci associated with educational attainment. Nature. Roozbeh M., Hesamian G., Akbari M.G., (2020). Ridge estimation in semi-parametric regression models under the stochastic restriction and correlated elliptically contoured errors. J Comput. Appl. Math. 37:112940. Rasekh A. R. (2006). Local influence in measurement error models with ridge estimate, comput. Stat. Data Anal, 50: 2822–2834. Rasekh A.R., Fieller N.R.J. (2003). Influence functions in functional measurement error models with replicated data. Statistics 37 (2), 169178. Rietveld CA et al. (2013). GWAS of 126,559 Individuals identifies genetic variants associated with educational attainment. Science 340(6139), 1467-1471. Saleh A. M. E., Arashi M. and Kibria G. (2019) Theory of Ridge Regression Estimation with Applications, John Wiley, USA. Saleh E., Shalabh (2014). Ridge regression estimation approach to measurement error model, J. Multivariate Analysis. 123, 68-84. Sheikhi A., Bahador F., Arashi M., (2020). On a generalization of the test of en- dogeneity in a two stage least squares estimation. Journal of Applied Statistics, DOI: 10.1080/02664763.2020.1837084. Singh S, Jain K, Sharma S. (2014). Replicated measurement error model under exact linear restrictions. Statist Pap. 55, 253-274. Martens E. P., Pestman W. R., de Boer A., Belitser S.V., Klungel O.H. (2006). In- strumental variables: application and limitations. Epidemiology. 17: 260267. Shalabh C.M., Paudel N.Kuma. (2009). Consistent estimation of regression param- eters under replicated ultrastructural model with non normal errors. J. Stat Comp Sim 79(3), 251-274. Wooldridge J. M. (2016). Introductory Econometrics: A Modern Approach 6th Edi- tion. Cengage Learning, Boston, MA. Wu D. M. (1973). Alternative tests of independence between stochastic regressors and disturbances. Econometrica, 42, 529-546.
  2. Akdeniz, F., and Roozbeh, M. (2017), Efficiency of the generalized-difference-based weighted mixed almost unbiased two-parameter estimator in partially linear model. Communications in Statistics - Theory and Methods, 46(24), 12259-12280. [DOI:10.1080/03610926.2017.1295075]
  3. Arashi, M.,Tabatabaey, S. M. M., and Hassanzadeh Bashtian, M. (2014), Shrinkage ridge estimators in linear regression. Communication in Statistics-Simulation and Computation, 43, 871-904. [DOI:10.1080/03610918.2012.718838]
  4. Bowden, R., and Turkington, D. (1984), Instrumental variables. Cambridge University Press, NY. [DOI:10.1017/CCOL0521262410]
  5. Burgess, S., Small, D. S., and Thompson, S. G. (2017), A review of instrumental variable estimators for Mendelian randomization. Statistical Methods in Medical Research, 26(5), 2333-2355. [DOI:10.1177/0962280215597579]
  6. Burgess, S. and Dylan, S. (2016), Predicting the Direction of Causal Effect Based on an Instrumental Variable Analysis: A Cautionary Tale. J. Causal Infer., 4(1), 49-59. [DOI:10.1515/jci-2015-0024]
  7. Cao, C. Z., Lin, J. G., Shi, J. Q., Wang, W., and Zhang, X. Y. (2015), Multivariate measurement error models for replicated data under heavy-tailed distributions. Chemometrics, 8, 457-466. [DOI:10.1002/cem.2725]
  8. Carrasco, M. (2012). A regularization approach to the many instruments problem. Journal of Econometrics, 170(2), 383-398. [DOI:10.1016/j.jeconom.2012.05.012]
  9. Carrasco, M., and Tchuente, G. (2015), Regularized LIML for many instruments. Journal of Econometrics, 186(2), 427-442. [DOI:10.1016/j.jeconom.2015.02.018]
  10. Carroll, R., Ruppert, J. D., Stefanski, L. A., and Crainiceanu, C. M. (2006), Measurement Error in Nonlinear Models: A Modern Perspective, CRC Press, Boca Raton, Fla, 2nd edition, pp. 485. [DOI:10.1201/9781420010138]
  11. Chan, L. K., and Mak, T. K. (1979), On the maximum likelihood estimation of a linear structural relationship when the intercept is known. J. Multivar. Anal., 9, 304-313. [DOI:10.1016/0047-259X(79)90087-3]
  12. Devanarayana, V., and Stefanski, L. A. (2002), Empirical Simulation Extrapolation for Measurement Error Models With Replicate Measurements, Statistics and Probability Letters, 59, 219-225. [DOI:10.1016/S0167-7152(02)00098-6]
  13. Didelez, V., and Sheehan, N. A. (2007), Mendelian randomization as an instrumental variable approach to causal inference. Stat. Meth. Med. Res., 16, 309-330. [DOI:10.1177/0962280206077743]
  14. Ebbes, P. (2004), Latent Instrumental Variables - A New Approach to Solve for Endogeneity. Ph.D.thesis, University of Groningen Economics and Business.
  15. Golub, G. H., Heath, M., and Wahba, G. (1979). Generalized cross-validation as a method for choosing a good ridge parameter. Technometrics, 21, 215-223. [DOI:10.1080/00401706.1979.10489751]
  16. Lawlor, D. A., Harbord, R. M., Sterne, J. A., Timpson, N., and Smith, G. D. (2008), Mendelian randomization: using genes as instruments for making causal inferences in epidemiology. Statistics in Medicine, 27(8), 1133-1163. [DOI:10.1002/sim.3034]
  17. Liu, X. Q., and Jiang, H. Y. (2012), Optimal generalized ridge estimator under the generalized cross-validation criterion in linear regression. Linear Algebra and its Applications, 436(5), 1238-1245. [DOI:10.1016/j.laa.2011.08.032]
  18. Fallah, R., Arashi, M., and Tabatabaey, S. M. M. (2017), On the ridge regression estimator with sub- space restriction, Communication in Statistics - Theory and Methods, 46(23), 11854-11865. [DOI:10.1080/03610926.2017.1285928]
  19. Ghapani, F., Babadi, B. (2016), A New Ridge Estimator in Linear Measurement Error Model with Stochastic Linear Restrictions. JIRSS, 15(2), 87-103. [DOI:10.18869/acadpub.jirss.15.2.87]
  20. Hausman, J. A. (1978), Specification tests in econometrics. Econometrica, 46, 1251-1271. [DOI:10.2307/1913827]
  21. Hansen, C., and Kozbur, D. (2014), Instrumental Variables Estimation with Many Weak Instruments Using Regularized JIVE. Journal of Econometrics, 182(2), 290-308. [DOI:10.1016/j.jeconom.2014.04.022]
  22. Harris, M. H., Gold, D. R., Rifas-Shiman, S. L., Melly, S.J., Zanobetti, A., Coul, B. A., Schwartz, J. D., Gryparis ,A., Kloog, I., and Koutrakis, P. (2016), Prenatal and childhood traffic-related air pollution exposure and childhood executive function and behavior. Neurotoxicol. Teratol., 57, 60-70. [DOI:10.1016/j.ntt.2016.06.008]
  23. Horel, A. E., and Kennard, R. W. (1970), Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12, 55- 83. [DOI:10.1080/00401706.1970.10488634]
  24. Isogawa, Y. (1985), Estimating a multivariate linear structural relationship with replication. J. R. Statist. Soc. B, 47, 211-215. [DOI:10.1111/j.2517-6161.1985.tb01347.x]
  25. Lachos, B. G., and Bolfarine, H. (2016), Heavy tailed calibration model with Berkson measurement errors for replicated data. Chemometrics and Intelligent Laboratory systems, 156, 21-35. [DOI:10.1016/j.chemolab.2016.04.014]
  26. Lousdal, M. L. (2018), An introduction to instrumental variable assumptions, validation and estimation. Emerging themes in epidemiology, 15(1), 1-7. [DOI:10.1186/s12982-018-0069-7]
  27. Nawarathna, L. S., and Choudhary, P. K. (2015), A Heteroscedastic Measurement Error Model for Method Comparison Data With Replicate Measurements. Statistics in Medicine, 34(7), 1242-1258. [DOI:10.1002/sim.6424]
  28. Okbay, A. et al. (2016), Genome-wide association study identifies 74 loci associated with educational attainment. Nature.
  29. Roozbeh, M., Hesamian, G., Akbari, M. G., (2020), Ridge estimation in semi-parametric regression models under the stochastic restriction and correlated elliptically contoured errors. J Comput. Appl. Math., 378, 112940. [DOI:10.1016/j.cam.2020.112940]
  30. Rasekh, A. R. (2006), Local influence in measurement error models with ridge estimate. comput. Stat. Data Anal, 50, 2822-2834. [DOI:10.1016/j.csda.2005.04.022]
  31. Rasekh, A. R., Fieller, N. R. J. (2003), Influence functions in functional measurement error models with replicated data. Statistics, 37(2), 169-178. [DOI:10.1080/0233188031000112890]
  32. Rietveld, C. A. et al. (2013), GWAS of 126,559 Individuals identifies genetic variants associated with educational attainment. Science, 340(6139), 1467-1471.
  33. Saleh, A. M. E., Arashi, M., and Kibria, G. (2019), Theory of Ridge Regression Estimation with Applications. John Wiley, USA. [DOI:10.1002/9781118644478]
  34. Saleh, E., and Shalabh (2014), Ridge regression estimation approach to measurement error model, J. Multivariate Analysis., 123, 68-84. [DOI:10.1016/j.jmva.2013.08.014]
  35. Sheikhi, A., Bahador, F., Arashi, M. (2020), On a generalization of the test of endogeneity in a two stage least squares estimation. Journal of Applied Statistics, DOI: 10.1080/02664763.2020.1837084. [DOI:10.1080/02664763.2020.1837084]
  36. Singh, S., Jain, K., Sharma, S. (2014), Replicated measurement error model under exact linear restrictions. Statist Pap., 55, 253-274. [DOI:10.1007/s00362-012-0469-7]
  37. Martens, E. P., Pestman, W. R., de Boer, A., Belitser, S. V., and Klungel, O. H. (2006), Instrumental variables: application and limitations. Epidemiology, 17, 260-267. [DOI:10.1097/01.ede.0000215160.88317.cb]
  38. Shalabh, C. M., and Paudel, N. K. (2009), Consistent estimation of regression parameters under replicated ultrastructural model with non normal errors. J. Stat Comp Sim, 79(3), 251-274. [DOI:10.1080/00949650701748556]
  39. Wooldridge, J. M. (2016), Introductory Econometrics: A Modern Approach 6th Edition. Cengage Learning, Boston, MA.
  40. Wu, D. M. (1973), Alternative tests of independence between stochastic regressors and disturbances. Econometrica, 42, 529-546. [DOI:10.2307/1911789]
Journal of the Iranian Statistical Society
Volume 19, Issue 2
December 2020
Pages 15-31
  • Receive Date: 23 July 2022
  • Revise Date: 10 May 2024
  • Accept Date: 23 July 2022