This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 573
Type: Topic Contributed
Date/Time: Wednesday, August 4, 2010 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Learning and Data Mining
Abstract - #307382
Title: Accurate Parameter Estimation Using High-Dimensional Astrophysical Data
Author(s): Joseph William Richards*+
Companies: Carnegie Mellon University
Address: 5000 Forbes Avenue, Pittsburgh, PA, 15213,
Keywords: manifold learning ; diffusion map ; dimension reduction ; astrostatistics ; basis learning
Abstract:

An important problem is how to properly analyze high-dimensional data that resides near a lower-dimensional manifold. This problem arises often in astrophysics, where, though data can be high-dimensional, the underlying models have only a few parameters. The diffusion map method is an effective means to analyze high-dimensional data with low-dimensional structure. The novelty of the diffusion map is that it creates a simple coordinate system in which Euclidean distances between data points accurately describe their degree of dissimilarity. Recently, we have used diffusion map for basis learning in a set of high-dimensional simple stellar population spectra. Particularly, we show how, for a database of galaxies, the diffusion map basis can be used along with astrophysical model fitting to obtain more accurate estimates of star formation history parameters than those in the literature.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.