Time-varying coefficient (TVC) estimation is a technique that has been developed to produce consistent estimates of parameters in the simultaneous face of measurement errors, unknown functional form and omitted variables. Previous work on the technique has not paid explicit attention to the...

Varying-coefficient models are useful tools for analyzing longitudinal data. They can effectively describe a relationship between predictors and responses which are repeatedly measured. We consider the problem of selecting variables in the varying-coefficient models via adaptive elastic net...

This article focuses on the estimation of the parametric component, which is of primary interest, in semi-varying coefficient models with heteroscedastic errors. Specifically, we first present a procedure for estimating the variance function of the error term and the resulting estimator is...