Parametric modeling of quantile regression coefficient functions with censored and truncated data

Area of Science:

• Statistics
• Econometrics
• Biostatistics

Background:

• Quantile regression coefficient functions model coefficient dependence on quantile order.
• Existing methods lack extensions for censored and truncated data.
• Parametric modeling of coefficient functions is an active research area.

Purpose of the Study:

• To extend parametric modeling of quantile regression coefficient functions to censored and truncated data.
• To propose a novel estimator for such data.
• To provide theoretical and practical tools for analysis.

Main Methods:

• Development of a new parametric estimator for quantile regression coefficient functions.
• Derivation of the estimator's asymptotic properties.
• Implementation of the estimator in the R package qrcm.

Main Results:

• The proposed estimator is theoretically sound with derived asymptotic properties.
• Goodness-of-fit measures are discussed for model evaluation.
• Simulation studies and real-data analysis demonstrate the estimator's utility.

Conclusions:

• The extended framework effectively handles censored and truncated data in quantile regression.
• The R package qrcm provides a practical tool for applying the new methodology.
• This work advances statistical modeling for survival and longitudinal data.