A vast range of statistical problems arises in modern astronomical research, particularly due to the flood of data produced by astronomical surveys at many wavebands. Equally important is the great increase in the complexity of the data sets, and while the scientific promise is tremendous, it depends critically on the ability to extract useful knowledge. This is a multifaceted project encompassing interdisciplinary astrostatistical research, with novel educational and outreach efforts. Specific projects include maximum-likelihood and resampling methods, computational algorithms for statistics for extremely large streaming datasets, the real-time classification of variable objects, hidden Markov models for stellar activity time series, and the treatment of missing data from small high-dimensionality datasets. There will be a particular emphasis on addressing the needs of the emerging Virtual Observatory.
Broader impacts include the development and offering of summer tutorials, both locally and on the Web, providing improved access to advanced statistical procedures, hosting active associates, and sponsoring astrostatistical conferences and sessions. Short intensive courses will help in training of graduate students and young researchers: advances in statistics will be brought into the toolbox of practicing scientists.
