Abstract
Kink model is developed to analyze the data where the regression function is two-stage piecewise linear with respect to the threshold covariate but continuous at an unknown kink point. In quantile regression for longitudinal data, kink point where the kink effect happens is often assumed to be heterogeneous across different quantiles. However, the kink point tends to be the same across different quantiles, especially in a region of neighboring quantile levels. Incorporating such homogeneity information could increase the estimation efficiency of the common kink point. In this paper, we propose a composite quantile estimation approach for the common kink point by combining information from multiple neighboring quantiles. Asymptotic normality of the proposed estimator is studied. In addition, we also develop a sup-likelihood-ratio test to check the existence of the kink effect at a given quantile level. A test-inversion confidence interval for the common kink point is also developed based on the quantile rank score test. The simulation studies show that the proposed composite kink estimator is more efficient than the single quantile regression estimator. We also illustrate the proposed method via an application to a longitudinal data set on blood pressure and body mass index.
References
Bondell, H. D., Reich, B. J., Wang, H.: Noncrossing quantile regression curve estimation. Biometrika, 97, 825–838 (2010)
Fan, J., Li, R.: Variable selection via nonconcave penalized likelihood and its oracle properties. J. Amer. Statist. Assoc., 96, 1348–1360 (2001)
Fong, Y., Di, C., Huang, Y., et al.: Model-robust inference for continuous threshold regression models. Biometrics, 73, 452–462 (2017)
Galvao, A. F., Kato, K., Montes-Rojas, G., et al.: Testing linearity against threshold effects: uniform inference in quantile regression. Ann. Inst. Statist. Math., 66, 413–439 (2014)
Hall, P., Sheather, S. J.: On the distribution of a studentized quantile. J. R. Stat. Soc. Ser. B Stat. Methodol., 50, 381–391 (1988)
Hansen, B. E.: Regression kink with an unknown threshold. J. Bus. Econom. Statist., 35, 228–240 (2017)
He, J., Klag, M. J., Whelton, P. K., et al.: Body mass and blood pressure in a lean population in southwestern china. American Journal of Epidemiology, 139, 380–389 (1994)
He, X., Shao, Q.-M.: A general Bahadur representation of M-estimators and its application to linear regression with nonstochastic designs. Ann. Statist., 24, 2608–2630 (1996)
He, X., Shao, Q.-M.: On parameters of increasing dimensions. J. Multivariate Anal., 73, 120–135 (2000)
Hendricks, W., Koenker, R.: Hierarchical spline models for conditional quantiles and the demand for electricity. J. Amer. Statist. Assoc., 87, 58–68 (1992)
Jiang, L., Bondell, H. D., Wang, H. J.: Interquantile shrinkage and variable selection in quantile regression. Comput. Statist. Data Anal., 69, 208–219 (2014)
Jiang, L., Wang, H. J., Bondell, H. D.: Interquantile shrinkage in regression models. J. Comput. Graph. Statist., 22, 970–986 (2013)
Kai, B., Li, R., Zou, H.: Local composite quantile regression smoothing: an efficient and safe alternative to local polynomial regression. J. R. Stat. Soc. Ser. B Stat. Methodol., 72, 49–69 (2010)
Kerry, S. M., Micah, F. B., Plange-Rhule, J., et al.: Blood pressure and body mass index in lean rural and semi-urban subjects in west africa. Journal of Hypertension, 23, 1645–1651 (2005)
Koenker, R.: Quantile regression for longitudinal data. J. Multivariate Anal., 91, 74–89 (2004)
Lee, J., Sun, Y., Wang, H.: Spatial cluster detection with threshold quantile regression. Environmetrics, 32, e2696 (2021)
Lee, S., Seo, M. H., Shin, Y.: Testing for threshold effects in regression models. J. Amer. Statist. Assoc., 106, 220–231 (2011)
Leng, C. Zhang, W.: Smoothing combined estimating equations in quantile regression for longitudinal data. Stat. Comput., 24, 123–136 (2014)
Li, C., Dowling, N. M., Chappell, R.: Quantile regression with a change-point model for longitudinal data: An application to the study of cognitive changes in preclinical Alzheimer’s disease. Biometrics, 71, 625–635 (2015)
Li, C., Wei, Y., Chappell, R., et al.: Bent line quantile regression with application to an allometric study of land mammals speed and mass. Biometrics, 67, 242–249 (2011)
Tang, C. Y., Leng, C.: Empirical likelihood and quantile regression in longitudinal data analysis. Biometrika, 98, 1001–1006 (2011)
Tang, Y., Wang, Y., Li, J., et al.: Improving estimation efficiency in quantile regression with longitudinal data. J. Statist. Plann. Inference, 165, 38–55 (2015)
Tesfaye, F., Nawi, N., Van Minh, H., et al.: Association between body mass index and blood pressure across three populations in africa and asia. Journal of Human Hypertension, 21, 28–37 (2007)
Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B Stat. Methodol., 58, 267–288 (1996)
Wang, H. J., Feng, X., Dong, C.: Copula-based quantile regression for longitudinal data. Statist. Sinica, 29, 245–264 (2019)
Zhang, L., Wang, H. J., Zhu, Z.: Testing for change points due to a covariate threshold in quantile regression. Statist. Sinica, 24, 1859–1877 (2014)
Zhang, L., Wang, H. J., Zhu, Z.: Composite change point estimation for bent line quantile regression. Ann. Inst. Statist. Math., 69, 145–168 (2017)
Zhong, W., Wan, C., Zhang, W.: Estimation and inference for multi-kink quantile regression. J. Bus. Econom. Statist., 40, 1123–1139 (2022)
Zou, H., Yuan, M.: Composite quantile regression and the oracle model selection theory. Ann. Statist., 36, 1108–1126 (2008)
Acknowledgements
We thank the Editor, the Associate Editor and three referees for their encouragements and insightful comments which have substantially improved the paper.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Natural Science Foundation of China (Grant Nos. 11922117, 11771361) and Fujian Provincial Science Fund for Distinguished Young Scholars (Grant No. 2019J06004)
Rights and permissions
About this article
Cite this article
Wan, C., Zhong, W. & Fang, Y. Composite Quantile Estimation for Kink Model with Longitudinal Data. Acta. Math. Sin.-English Ser. 39, 412–438 (2023). https://doi.org/10.1007/s10114-023-1557-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10114-023-1557-4
Keywords
- Asymptotical normality
- composite quantile estimation
- estimation efficiency
- kink design model
- longitudinal data