Saturday, May 4, 2013

All About Spherically Distributed Regression Errors

In our list of standard assumptions about the error term in linear multiple regression model, we include one that incorporates both homoskedasticity and the absence of autocorrelation. That is, the individual values of the errors are assumed to be generated by a random process whose variance is constant, and all possible distinct pairs of these values are uncorrelated. This implies that the full error vector has a scalar covariance matrix.
This overall situation is referred to as one in which the values of the error term follow a “Spherical Distribution”. Let's take a look at the origin of this terminology.

http://www.r-bloggers.com/all-about-spherically-distributed-regression-errors/

How R Grows

Tabulating the packages by publication date could give some indication of how much effort is being expended to improve packages and keep them up to date. Most CRAN packages which are available currently were either created or updated in the last year or so. Apparently, only 264 packages haven’t been touched since 2010 or before. Here is a graphical study of the same:

http://www.r-bloggers.com/how-r-grows/

Thursday, May 2, 2013

Statistics2013 Video Contest Results

After 100 Years, Ramanujan Gap Filled

A century ago, Srinivasa Ramanujan and G. H. Hardy started a famous correspondence about mathematics so amazing that Hardy described it as “scarcely possible to believe.” In 1919 Ramanujan was deathly ill while on a long ride back to India, from February 27 to March 13 on the steamship Nagoya. All he had was a pen and pad of paper and he wanted to write down his equations before he died. He wrote an incomplete equation which has been solved after a gap of 100 years:

http://blog.wolfram.com/2013/05/01/after-100-years-ramanujan-gap-filled/