Astrostatistics

check here for Penn State's new
Center for Astrostatistics

Researchers in observational astronomy often encounter situations where the scientific goals require a statistical interpretation of rather complex data. These problems cover a vast range of statistical issues, such as:

For the past decade, Dr. Feigelson has worked with statisticians at Penn State to address such questions. Some efforts have been made to develop new techniques specifically for astrostatistics. But much can be learned by applying methods already known to statisticians to astronomical problems. Dr. Feigelson and his colleagues Drs. G. Jogesh Babu and Michael Akritas have been leaders in the advancement of statistical methodology for astronomical research.

Feigelson and Babu organized international conferences called Statistical Challenges in Modern Astronomy (SCMA) held at Penn State. The purpose is to enhance the dialog between astronomers and statisticians on important research issues. Proceedings of the first (1991), second (1996) and  third   (2001) SCMA conferences are available.  In 1996, we wrioe a brief  monograph called Astrostatistics which introduces astronomer and statistician readers to the other field, and provides the first overview of astrostatistical issues. An extensive bibliography and index assists readers in pursuing topics introduced in the book.   Drs. Feigelson and Babu have spoken at many meetings in both fields, promoting improvments in statistical methodology for observational astronomy, with an emphasis on time series analysis and multivariate analysis.  In the latter context, we published a multivariate study of gamma-ray bursts   which reports the discovery of a new class of GRBs.

During the late 1990s, Dr. Feigelson joined with Drs. Akritas in Statistics to form the Statistical Consulting Center for Astronomy. Operating by email and WWW, it gave quick reliable statistical advice for practicing astronomers as they encounter statistical problems. A wide range of problems are addressed such as appropriate treatment of known measurement errors, interpretation of Poisson processes, and parameter estimation in nonlinear regression.

We also created a popular Web metasite called StatCodes which provides hypertext links to many statistical codes and services on the Web. Among many codes available from StatCodes are three developed at Penn State: ASURV   implementing a suite of survival methods treating censored data (i.e. with nondetections), SLOPES   and BCES providing several weighted and unweighted linear regressions with analytical and bootstrap error analysis, and  CENS_TAU   for estimating correlation in multiply-censored multivariate datasets.