High-Dimensional Statistics: Non-Parametric Generalized Functional Partially Linear Single-Index Model

We study the non-parametric estimation of partially linear generalized single-index functional models, where systematic component model has a flexible semi-parametric form with general link function. suggest an efficient and practical approach to estimate (I) function, (II) coefficients as well (III) model. The procedure is developed by applying quasi-likelihood, polynomial splines kernel smoothings. then derive asymptotic properties, rates, estimators each Their normality also established. By making use approximation Fisher scoring algorithm, we show that our numerical advantages in terms efficiency computational stability. A on data provided illustrate good behavior methodology.