NONPARAMETRIC ESTIMATORS FOR TIME SERIES

作者：Peter M. Robinson · 发表于：Journal of Time Series Analysis · 年份：1983 · DOI：10.1111/j.1467-9892.1983.tb00368.x · 被引用次数：570 · 研究领域：Financial Risk and Volatility Modeling、Statistical Methods and Inference、Advanced Statistical Methods and Models

Abstract.Kernel multivariate probability density and regression estimators are applied to a univariate strictly stationary time seriesXrWe consider estimators of the joint probability density ofXtat differentt‐values, of conditional probability densities, and of the conditional expectation of functionals ofXvgiven past behaviour. The methods seem of particular relevance in light of recent interest in non‐Gaussian time series models. Under a strong mixing condition multivariate central limit theorems for estimators at distinct points are established, the asymptotic distributions being of the same nature as those which would derive from independent multivariate observations.