Abstract
We consider a generalization of local-linear regression for estimation of compnents' regression functions by observations from mixture with varying concentrations. A cross-validation technique is developed for the bahdwidth selection. Performance of the obtained estimator is compared with the modified Nadaraya-Watson estimator performance by simulations.
Publisher
Taras Shevchenko National University of Kyiv
Subject
Medical Assisting and Transcription,Medical Terminology
Reference7 articles.
1. 1. MAIBORODA R., SUGAKOVA O. (2008) Otsiniuvannia ta klasyfikatsiia za sposterezhenniamy iz sumishi. Kyiv: Kyivskyi universytet, 213 p.
2. 2. A. PIDNEBESNA, I. FAJNEROV'A, J. HOR'Av{C}EK, J. HLINKA. (2023)
3. 3. Mixture Components Inference for Sparse Regression: Introduction and Application for Estimation of Neuronal Signal from fMRI BOLD. In Applied Mathematical Modelling, Vol. 116, p. 735-748.
4. 4. DYCHKO H., MAIBORODA R. (2020) A generalized Nadaraya-Watson estimator for observations obtained from a mixture. In Theory of Probability and Mathematical Statistics, Vol. 100, p. 61-76, DOI: 10.1090/tpms/1098.
5. On Estimating Regression;NADARAYA;In Theory of Probability and its Applications Vol 9 No 1,1964
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献