Two-stage orthogonality based estimation for semiparametric varying-coefficient models and its applications in...

Area of Science:

• Statistics
• Biostatistics
• Longitudinal Data Analysis

Background:

• Longitudinal data analysis often employs semiparametric smoothing methods.
• Improving regression coefficient efficiency in these models is a key research interest.

Purpose of the Study:

• To propose a novel two-stage orthogonality-based method for estimating parameters in semiparametric varying-coefficient models (SVCMs) for longitudinal data.
• To enhance the efficiency of estimating parameter vectors, coefficient function vectors, and covariance functions.

Main Methods:

• Utilizes orthogonal projection, local linear technique, quasi-score estimation, and quasi-maximum likelihood estimation.
• A two-stage approach allows for separate implementation of estimators without mutual interference.

Main Results:

• Asymptotic properties of the proposed estimators are established under mild conditions.
• The asymptotic behavior of coefficient function vector estimators at boundaries is specifically examined.
• Monte Carlo simulations demonstrate the finite sample performance of the methodology.

Conclusions:

• The proposed two-stage method offers an efficient approach for SVCMs with longitudinal data.
• The methodology is validated through theoretical analysis and simulation studies.
• The approach is practically demonstrated using an acquired immune deficiency syndrome (AIDS) dataset.