Aug 14th, 2007| 10:17 pm | Posted by hlee
During the International X-ray Summer School, as a project presentation, I tried to explain the inadequate practice of χ^2 statistics in astronomy. If your best fit is biased (any misidentification of a model easily causes such bias), do not use χ^2 statistics to get 1σ error for the 68% chance of capturing the true parameter.
Later, I decided to do further investigation on that subject and this paper came along: Astrostatistics: Goodness-of-Fit and All That! by Babu and Feigelson.
Continue reading ‘Astrostatistics: Goodness-of-Fit and All That!’ »
Tags:
Anderson-Darling,
Babu,
best-fit,
bias,
bootstrap,
chi-square,
Cramer-von Mises,
Feigelson,
Kolmogorov-Smirnoff,
Kullback-Leibler distance,
nonparametric,
parametric,
resampling Category:
Algorithms,
arXiv,
Astro,
Fitting,
High-Energy,
Methods,
Spectral,
Stat |
7 Comments
Jan 29th, 2007| 12:34 am | Posted by hlee
Since Summer 2005, G. Jogesh Babu (Statistics) and Eric Feigelson (Astronomy) have organized lectures and lab sessions on statistics for astronomers and physicists. Lecturers are professors from Penn State statistics department and invited renown scientists from different countries. Students show diverse demography as well. Within a week or so, students listen Statistics 101 to recently published statistical theories particularly applied to astronomical data. They also learn how to use R, a statistical software and script language to perform statistics they learn through lectures. Past two years, this summer school proved its uniqueness and usefulness. More information on the upcoming school can be found at http://astrostatistics.psu.edu/su07/index.html and other topics regarding astrostatistics at Center for AstroStatistics at Penn State.