Discussing with a non statistician colleague, it seems that the logistic regression is not intuitive; Some basics questions like : - Why don't use the linear model? - What's logistic function? - How can we compute by hand, step by step t...

This function generates nice looking tree diagrams (see sample) below from tree objects (generated by package tree). This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option)

What happens when you plot billions of geotagged Tweets on a map? You can see the arteries of the world. Here's Europe: According to creator Miguel Rios (Engineering Manager, Data Visualization at Twitter), the dots on this chart represent every geotagged Tweet since 2009. The color represents number of tweets in the region, and the intensity shows where people...

Yesterday, Daniel Marcelino published an interesting post on his blog, untitled Parallel Processing: When does it worth ? I was asking myself the same question for a chapter I am currently writing. And I did like his approach, so I tried, on my computer to do the same. I did use three packages to run parallel R codes, >...

A while ago I was playing around with the JavaScript package D3.js, and I began with this visualization—that I never really finished—of how a one-way ANOVA is calculated. I wanted to make the visualization interactive, and I did integrate some interactive elements. For instance, if you hover over a data point it will show the residual, and its value will be highlighted in...

Here are comments by Olli following my post: I think we found a general means to obtain accurate ABC in the sense of matching the posterior mean or MAP exactly, and then minimising the KL distance between the true posterior and its ABC approximation subject to this condition. The construction works on an auxiliary probability

Last time I wrote about version control using Subversion (and its implementation in Eclipse). I still haven’t given up on it, but since I’m using a private repository, sharing code has been a bit tedious. I was introduced to git a while ago, but somehow decided to go for Subversion. A few days ago a

In a recent tutorial in the eLife journal, Huang, Rattner, Liu & Nathans suggested that researchers who draw scatterplots should start providing not one but three regression lines. I quote, Plotting both regression lines gives a fuller picture of the data, and comparing their slopes provides a simple graphical assessment of the correlation coefficient. Plotting

I’ll be contributing a piece about once a week for the Guardian Australia, under a part of the web site we’re calling The Swing. The set of graphs from my 1st effort were rendered in-line and rather low-res. Bigger, full res versions appear below; click on the in-line versions. It would be great to find

by Joseph Rickert In a post last week, I offered some first impressions about R/Finance 2013. Apparently, I was way off in estimating that 30% of the attendees were academics. The R/Finance organizers were quick to point out that percentage of academics attending the conference has been a constant 10% over the years; and this year was no different....

The practice of classifying treatments as empirically supported (ESTs) has been widely debated for a long time. Recently Jessica Nasser published an article in the Journal of Contemporary Psychotherapy named “Empirically Supported Treatments and Efficacy Trials: What Steps Do We Still Need to Take?”. In the article the author raises several concerns and suggestions regarding the current use of...

It is getting easier to get data directly into R from the web. Often R packages that retrieve data from the web return useful R data structures like a data.frame or plot. This is a good thing of course to make things user friendly. However, what if you want to drill down into the data that's returned from a query...

Most computers nowadays have few cores that incredibly help us with our daily computing duties. However, when statistical softwares do use parallelization for analyzing data faster? R, my preferred analytical package, does not take too much advantage of multicore processing by default. In fact, R has been inherently a “single-processor” package until nowadays. Stata, another

Today I learned about two forthcoming R books that I'm now looking forward to. The first is Applied Predictive Modeling by Max Kuhn and Kjell Johnson. Max Kuhn is the author of the caret package, an extremely useful and powerful R package for fitting and optimizing all kinds of predictive models in R. It's available now on Amazon Kindle...

A couple of years ago I implemented an automated trading algorithm for a strategy called the “Cable Morning Trade”. The basis of the strategy is the range of GBPUSD during the interval 05:00 to 09:00 London time. Two buy stop orders are placed 5 points above the highest high for this period; two sell stop