Some automated methods of smoothing time-dependent data

摘要: Nonparametric function estimation based upon time-dependent data is a challenging problem to both the analyst and theoretician. This paper serves as an introduction discusses some of approaches that have been proposed for smoothing autocorrelated data. A principal theme will be accounting correlation in driven choice estimator's parameter. Data-driven considered various settings including probability density estimation, repeated measures data, time series trend estimation. Both applications theoretical issues are addressed, open problems discussed.