Strong uniform consistency and asymptotic normality of a kernel based error density estimator in functional autoregressive models
Authors:
Preprint
Abstract
Estimating the innovation probability density is an important issue in any regression analysis. This paper focuses on functional autoregressive models. A residual-based kernel estimator is proposed for the innovation density. Asymptotic properties of this estimator depend on the average prediction error of the functional autoregressive function. Sufficient conditions are studied to provide strong uniform consistency and asymptotic normality of the kernel density estimator.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Global property of error density estimation in nonlinear autoregressive time series modelsStatistical Inference for Stochastic Processes, 2010
- Kernel Density Estimation and Goodness-of-Fit Test in Adaptive TrackingSIAM Journal on Control and Optimization, 2008
- A note on the Bickel–Rosenblatt test in autoregressive time seriesStatistics & Probability Letters, 2005
- Weak and strong uniform consistency of a kernel error density estimator in nonparametric regressionJournal of Statistical Planning and Inference, 2004
- On the Bickel–Rosenblatt test for first-order autoregressive modelsStatistics & Probability Letters, 2002
- Combinatorial Methods in Density Estimation2001
- Uniform iterated logarithm laws for martingales and their application to functional estimation in controlled Markov chainsStochastic Processes and their Applications, 2000
- Estimating the Density of the Residuals in Autoregressive ModelsStatistical Inference for Stochastic Processes, 1999
- Residuals density estimation in nonparametric regressionStatistics & Probability Letters, 1992
- Consistent nonparametric estimation of error distributions in linear modelActa Mathematicae Applicatae Sinica, English Series, 1991