Regression Analysis of Doubly Truncated Data

• Published in: Journal of the American Statistical Association Vol. 115; no. 530; pp. 810 - 821
• Main Authors: Ying, Zhiliang, Yu, Wen, Zhao, Ziqiang, Zheng, Ming
• Format: Journal Article
• Language: English
• Published: United States Taylor & Francis 02.04.2020; Taylor & Francis Ltd
• Subjects: Acquired immune deficiency syndrome; AIDS; Astronomy; Computer simulation; computer software; Counting; data collection; Dependent variables; Econometrics; Empirical process; Intervals; Justification; Mann-Whitney U test; Parameter estimation; Quasars; Rank estimation; Regression analysis; Resampling; Simulation; Statistical methods; Statistics; Survival analysis; U-process; Wilcoxon-Mann-Whitney statistic; Empirical process; Wilcoxon-Mann-Whitney Statistic; Linear programming; L1 method; Resampling; U-process; Confidence interval; Rank estimation
• DOI: 10.1080/01621459.2019.1585252
• ISSN: 0162-1459; 1537-274X

Doubly truncated data are found in astronomy, econometrics, and survival analysis literature. They arise when each observation is confined to an interval, that is, only those which fall within their respective intervals are observed along with the intervals. Unlike the one-sided truncation that can be handled by counting process-based approach, doubly truncated data are much more difficult to handle. In their analysis of an astronomical dataset, Efron and Petrosian proposed some nonparametric methods for doubly truncated data. Motivated by their approach, as well as by the work of Bhattacharya et al. for right truncated data, we propose a general method for estimating the regression parameter when the dependent variable is subject to the double truncation. It extends the Mann-Whitney-type rank estimator and can be computed easily by existing software packages. Weighted rank estimation is also considered for improving estimation efficiency. We show that the resulting estimators are consistent and asymptotically normal. Resampling schemes are proposed with large sample justification for approximating the limiting distributions. The quasar data in Efron and Petrosian and an AIDS incubation data are analyzed by the new method. Simulation results show that the proposed method works well.