May 28th, 2009| 11:54 pm | Posted by hlee

This simple law, despite my trial of full text search, was not showing in ADS. As discussed in systematic errors, astronomers, like physicists, show their error components in two additive terms; statistical error + systematic error. To explain such decomposition and to make error analysis statistically rigorous, the **law of total variance (LTV)** seems indispensable. Continue reading ‘[MADS] Law of Total Variance’ »

Tags:

additive,

bias,

law of total variance,

MADS,

mathematical statistics,

mean integrated square error,

mean square error,

MISE,

mse,

probability theory,

variance Category:

Algorithms,

Data Processing,

Jargon,

News,

Stat,

Uncertainty |

Comment
May 27th, 2009| 03:45 pm | Posted by TomLoredo

I’ve copied below the text of an ISBA announcement for the first workshop in a new series addressing Bayesian methods for machine learning. It builds on the model of the earlier well-known “Bayesian case studies” workshops, where just a few applications are featured at each workshop, with the format tailored to produce a lot of back-and-forth between application scientists and statisticians.

One of the three topics for the October workshop is titled “Calibrating the Universe: a Bayesian Uncertainty Analysis of a Galaxy Simulation.” This sounds a bit reminiscent of the “cosmic calibration” work by a collaboration of astronomers and statisticians at Los Alamos. They are using a combination of parametric and nonparametric Bayesian methods and dimensional reduction and experimental design techniques to infer cosmological parameters from CMB, large scale structure, and Type Ia supernova data. Despite the similarity in nomenclature, this appears to be a different team and a different application. However, from what I can glean from the team, it’s the same kind of problem: implementing a parametric Bayesian analysis with a computationally expensive model, by building a fast nonparametric “emulator” for the model. Should be interesting.

Continue reading ‘Bayesian machine learning workshop, featuring an astronomy application’ »

May 21st, 2009| 05:55 pm | Posted by hlee

Among billion objects in our Galaxy, outside the Earth, our Sun drags most attention from astronomers. These astronomers go by solar physicists, who enjoy the most abundant data including 400 year long sunspot counts. Their joy is not only originated from the fascinating, active, and unpredictable characteristics of the Sun but also attributed to its influence on our daily lives. Related to the latter, sometimes studying the conditions on the Sun is called **space weather forecast.** Continue reading ‘space weather’ »

Tags:

classifier,

forecast,

logistic regression,

machine learning,

predictor,

response,

space weather,

Sun,

sunspot,

SVM,

test data,

training data,

weather Category:

arXiv,

Astro,

Cross-Cultural,

Data Processing,

Imaging,

Jargon,

Stars,

Stat |

Comment
May 18th, 2009| 12:18 pm | Posted by hlee

My understandings of **“robustness”** from the education in statistics and from communicating with astronomers are hard to find a mutual interest. Can anyone help me to build a robust bridge to get over this abyss? Continue reading ‘Robust Statistics’ »

Tags:

break point,

Huber,

nonparametric,

robust,

Rousseeuw,

Tukey Category:

Bayesian,

Frequentist,

Jargon,

MCMC,

Methods,

Quotes,

Stat,

Uncertainty |

Comment
May 7th, 2009| 02:22 pm | Posted by hlee

Almost 100 years ago, A.S. Eddington stated in his book *Stellar Movements* (1914) that

…in calculating the mean error of a series of observations it is preferable to use the simple mean residual irrespective of sign rather than the mean square residual

Such eminent astronomer said already *least absolute deviation* over *chi-square*, if I match *simple mean residual* and *mean square residual* to relevant methodologies, in order. Continue reading ‘a century ago’ »

Tags:

chi-square minimization,

Eddington,

inference,

LAD,

Laplace,

mse,

PyMC,

Python,

R.A.Fisher,

utility function Category:

Astro,

Cross-Cultural,

Quotes,

Stat,

Uncertainty |

Comment
May 7th, 2009| 11:14 am | Posted by hlee

One of [ArXiv] papers from yesterday whose title might drag lots of attentions from astronomers. Furthermore, it’s a short paper.

[arxiv:math.CO:0905.0483] by Harmany, Marcia, and Willet.

Continue reading ‘[ArXiv] Sparse Poisson Intensity Reconstruction Algorithms’ »

Tags:

compressed sensing,

decomposition,

EM algorithm,

intensity,

MPLE,

multiscale,

penalty,

Poisson,

Poisson Intensity,

Sparcity,

wavelet Category:

Algorithms,

arXiv,

Astro,

Cross-Cultural,

Data Processing,

High-Energy,

Imaging,

Jargon |

Comment
May 4th, 2009| 12:36 pm | Posted by vlk

For someone who doesn’t know any grammar, I can be a bit of a Grammar nazi sometimes. And one of my pet peeves is when people use the word *data* in the singular. No! Data **are!**

Or so I used to believe. Continue reading ‘Datums’ »