Asymptotic Statistical Analysis of Time Series: Clustering, Change Point, and Other Problems
May 28, 2013 2792 views 
A method for constructing asymptotically consistent efficient algorithms for various statistical problems concerning stationary ergodic time series is presented. The considered problems include clustering, hypothesis testing, change-point estimation and others. The presented approach is based on empirical estimates ofthe distributional distance. Some open problems are also discussed.