The San Francisco Bay Area ACM runs several courses on data mining and machine learning with R. Machine Learning 101 deals primarily with supervised learning problems, and Machine Learning 102 covers unsupervised learning and fault detection. Machine Learning 101 & 102 were most recently presented by Mike Bowles & Tricia Hoffman in September, and the lecture ... [Read more...]

[Read more...]

[Read more...]

The Global Historical Climate Network  (GHCN) is in it’s beta stage. On of the stated goals of the project is to improve the metadata that is provided for the station data.  Over the past few months several independent volunteers have been focusing on the issue of station metadata, each ... [Read more...]

Every academic field seems to develop a set of generic insults based on their intellectual toolkit. Here are two examples I hear often: Probabilists and Statisticians: “I think that’s an interesting case, but it’s in a set with measure zero.” Economists: “X group’s behavior is clearly rent-seeking.” ... [Read more...]

If you use lattice with R, and you need to plot confidence limits in your graphic, then panel.smoother and panel.quantile from latticeExtra will help you with this task. These functions internally calculate the error bounds and use panel.polygon from lattice. If you need to plot your own ... [Read more...]

Following on from the initial post about creating a document using LaTeX we need to consider the structure of the document, i.e. headings and page layout. Fast Tube by Casper Document Class The document class is a template that specifies the appearance of different components of a document, e.... [Read more...]

An the New York R User Group* last night, 100 R users heard Ni Wang and Max Lin talk explain how "R is one of the important tools used by analysts and engineers at Google for analyzing data". During the talk, Lin revealed that Google plans to make "R more integrated ... [Read more...]

Long time ago I stumbled across interesting volatility measurement at quantifiableedges.blogspot.com. The idea is following: take 3-day historical volatility of S&P 500 index and divide that by 10-day historical volatility. Then mark all points which are less that 0.25 and measure the volatility of 3 following days. On average, the ... [Read more...]

“The measurement outputs contain at the 99% confidence level 42 new random bits. This is a much stronger statement than passing or not passing statistical tests, which merely indicate that no obvious non-random patterns are present.” arXiv:0911.3427 As often, I bought La Recherche in the station newsagent for the wrong reason! The ... [Read more...]

If you're creating a bar chart in R, how do you decide what colors the bars should be? Or if you're creating an image plot, what range of images should you use? The colors you choose can not only affect the viewer's interpretation of the graphic, it can also determine ... [Read more...]

The version 0.21 of the solaR package is now available at CRAN. This package provides a set of calculation methods of solar radiation and performance of photovoltaic systems. The package has been uploaded to CRAN under the GPL-3 license. solaR is now able to calculate from both daily and sub-daily irradiation ... [Read more...]

If you missed today's webcast on Revolution R Enterprise: 100% R and more, the slides from the presentation are now available for download, and a replay of the webcast (in WMV format) will be available at that same link very soon. And if you missed some of the links I mentioned ... [Read more...]

Romain pushed verion 0.3.8 of inline to CRAN earlier today, and I just updated the Debian package. This version adds an internal performance enhancement which is obtained by making due with fewer reads. The short NEWS file entry follows: 0.3.8 2... [Read more...]

Last week, I received a box of books from the International Statistical Review, for reviewing them. I thus grabbed the one whose title was most appealing to me, namely Bayesian Model Selection and Statistical Modeling by Tomohiro Ando. I am indeed interested in both the nature of testing hypotheses or ... [Read more...]

The following simple code can be used to find roots of functions (based on the secant algorithm), secant=function(fun, x0, x1, tolerence=1e-07, niter=500){for ( i in 1:niter ) { x2 [Read more...]

The correlation coefficient is a measurement of correlation between two random variables. While its computation is straightforward, it is not readily applicable to non-parametric statistics. read more [Read more...]

I'll be hosting a webinar tomorrow (Wednesday) aimed at R users who want to know more about how Revolution R Enterprise extends open source R for big data, Web services, multi-core processing, debugging and more. For R users at schools and universities, I'll also explain how you can download and ... [Read more...]

R evangelist David Smith, marketing VP at Revolution R, will be giving a webinar showing off some of the finer features of Revolution R Enterprise - an integrated development environment (IDE) for R that has an enhanced script editor with syntax highli... [Read more...]

In the previous post (here) discussing forecasts of actuarial quantities, I did not mention much how to forecast the temporal component in the Lee-Carter model. Actually, many things can be done. Consider here some exponential smoothing techniques ... [Read more...]