eprintid: 1531 rev_number: 14 eprint_status: archive userid: 2 dir: disk0/00/00/15/31 datestamp: 2015-02-20 11:30:38 lastmod: 2017-02-08 12:21:35 status_changed: 2015-04-27 12:11:04 type: article metadata_visibility: show creators_name: Hart, Jeffrey corp_creators: Texas A&M University title: Some automated methods of smoothing time-dependent data ispublished: pub subjects: MP2 subjects: SS divisions: EPOS-P full_text_status: none keywords: Kernel estimators, mean integrated squared error, cross-validation, plug-in rules, autoregression, transition densities, block wise cross-validation, prequential analysis, time series cross-validation abstract: Nonparametric function estimation based upon time-dependent data is a challenging problem to both the data analyst and the theoretician. This paper serves as an introduction to the problem and discusses some of the approaches that have been proposed for smoothing autocorrelated data. A principal theme will be accounting for correlation in the data driven choice of a function estimator's smoothing parameter. Data-driven smoothing is considered in various settings including probability density estimation, repeated measures data, and time series trend estimation. Both applications and theoretical issues are addressed, and some open problems will be discussed. date: 1996 publication: Journal of Nonparametric Statistics volume: 6 number: 2-3 publisher: American Statistical Association pagerange: 115-142 id_number: doi:10.1080/10485259608832667 refereed: TRUE issn: 1048-5252 official_url: http://dx.doi.org/10.1080/10485259608832667 access_IS-EPOS: limited owner: Publisher citation: Hart, Jeffrey (1996) Some automated methods of smoothing time-dependent data. Journal of Nonparametric Statistics, 6 (2-3). pp. 115-142. DOI: https://doi.org/10.1080/10485259608832667