z-logo
Premium
Series Estimation in Partially Linear In‐Slide Regression Models
Author(s) -
YOU JINHONG,
ZHOU XIAN,
ZHOU YONG
Publication year - 2011
Publication title -
scandinavian journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.359
H-Index - 65
eISSN - 1467-9469
pISSN - 0303-6898
DOI - 10.1111/j.1467-9469.2010.00711.x
Subject(s) - mathematics , estimator , parametric statistics , semiparametric regression , series (stratigraphy) , least squares function approximation , semiparametric model , linear model , statistics , component (thermodynamics) , parametric model , generalized least squares , rate of convergence , computer science , paleontology , computer network , channel (broadcasting) , physics , biology , thermodynamics
Abstract.  The partially linear in‐slide model (PLIM) is a useful tool to make econometric analyses and to normalize microarray data. In this article, by using series approximations and a least squares procedure, we propose a semiparametric least squares estimator (SLSE) for the parametric component and a series estimator for the non‐parametric component. Under weaker conditions than those imposed in the literature, we show that the SLSE is asymptotically normal and that the series estimator attains the optimal convergence rate of non‐parametric regression. We also investigate the estimating problem of the error variance. In addition, we propose a wild block bootstrap‐based test for the form of the non‐parametric component. Some simulation studies are conducted to illustrate the finite sample performance of the proposed procedure. An example of application on a set of economical data is also illustrated.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here