Astrostatistics
Main Content
Questions
- How can we use statistical methods to maximize the quality and accuracy of information extracted from astronomical data sets?
- What statistical tools do we need to develop for analyzing the
vast data sets produced by facilities like Sloan Digital Sky Survey, Large Synoptic Survey Telescope, Expanded Very Large Array, and Atacama Large Millimeter Array? Computational efficiency is crucial for these problems.
- When does the spatial distribution of galaxies in a cluster indicate subclustering? When do groupings of photons on an X-ray detector indicate a source is extended? These questions lie in the purview of the well-established statistical field of spatial point processes.
- How does one establish luminosity functions, compare samples, or search for correlations in data subject to flux limits? Flux limits cause statistical censoring (i.e. non- detections of known objects) or truncation (i.e. faint objects are missing entirely).
- How can one best discriminate stars from galaxies in digital optical surveys? What is the most valid classification scheme for spiral galaxy morphologies or emission line AGN? How will lightcurves be classified from the Large Synoptic Survey Telescope database? These are questions in multivariate analysis, a huge field that is rarely tapped to solve astronomical problems.
- What are the best estimates of the parameters of the consensus LambdaCDM cosmological model based on cosmic microwave background, galaxy clustering and other observational constraints? This requires fusing nonlinear regressions of large datasets, and is often pursued using Bayesian methods.
- Can predictable timescales for flaring activity on cool stars be derived from data monitored continuously for extended periods of time? This involves the use of power spectrum analysis and the application of the phase dispersion minimization technique.
- Creation of the Center for Astrostatistics
- Every 5 years since 1991, Eric Feigelson and G. Jogesh Babu have organized an international conference called Statistical Challenges in Modern Astronomy (SCMA). The fifth installment will be held in June of 2011.
- Every summer since 2005, Eric Feigelson and G. Jogesh Babu have organized the Summer School in Statistics for Astronomers.
- Mercedes Richards has applied statistical methods to the study of long term continuous radio flare surveys of cool stars in close binary star systems.
- Mercedes Richards has performed a statistical analysis of sunspot number data to explain why the length of the sunspot cycle varies between 10 and 12 years by examining the long-term 188-year periodic cycle of variability in terms of historic sunspot minima like the Maunder Minimum.
- Eric Feigelson and G. Jogesh Babu are nearing completion of a new textbook on astrostatistics
- The Center is consulting with a variety of research groups on statistical issues including the National Radio Astronomy Observatory, Large Synoptic Survey Telescope, Virtual Astronomical Observatory, and Penn State's effort to trigger transient events using high-energy and gravitational wave observatories. The Center is nurturing astrostatistics organizations within the International Statistical Institute and International Astronomical Union.
- Faculty
G. Jogesh Babu (Statistics)
Links
- Center for Astrostatistics
- StatCodes - On-line Statistics Software
- Dr. Feigelson's Astrostatistics Site
- A detailed description of Mercedes Richards' work related to astrostatistics
- IAU Symposium 282: From Interacting Binaries to Exoplanets: Essential Modeling Tools
