Monthly Archives: September 2013

Regression on variables, or on categories?

September 30, 2013
By

I admit it, the title sounds weird. The problem I want to address this evening is related to the use of the stepwise procedure on a regression model, and to discuss the use of categorical variables (and possible misinterpreations). Consider the following dataset > db = read.table("http://freakonometrics.free.fr/db2.txt",header=TRUE,sep=";") First, let us change the reference in our categorical variable  (just to...

Read more »

Which is the best "Flyover" state?

September 30, 2013
By
Which is the best "Flyover" state?

If you were to hop into your personal aircraft, and plotted a straight line course taking off in one state and landing in the SAME state, how many other states might you fly over? On other words, what's the best state for "flyovers" of other states? Todd Schnieder from the Rapgenius engineering team answered that question using the R...

Read more »

How heavy is the Siberut macaque? A Bayesian phylogenetic approach

September 30, 2013
By
How heavy is the Siberut macaque? A Bayesian phylogenetic approach

Among-species comparisons can include phylogenetic information to account for non-independence arising from shared evolutionary history. Often, phylogenetic topologies and branch lengths are not known exactly, but are estimated with uncertainty. This uncertainty can be accounted for using methods recently described in a neat paper called Bayesian models for comparative analysis integrating phylogenetic uncertainty by Villemereuil et...

Read more »

An R function to download shapefiles

September 30, 2013
By
An R function to download shapefiles

This post is a follow up from my latest Things I Forget post on reading in shapefiles.  That post assumed that you already had access to all the relevant files (e.g. .shp, .shx, .prj, .dbf, etc.).  A task that I routinely need to do is locate shapefiles on a website, grab those files, and read

Read more »

A Bayesian Twist on Tukey’s Flogs

September 30, 2013
By
A Bayesian Twist on Tukey’s Flogs

In the last post I described flogs, a useful transform on proportions data introduced by John Tukey in his Exploratory Data Analysis. Flogging a proportion (such as, two out of three computers were Macs) consisted of two steps: first we “started” the proportion by adding 1/6 to each of the counts and then we “folded” it...

Read more »

ROC curves and classification

September 30, 2013
By
ROC curves and classification

To get back to a question asked after the last course (still on non-life insurance), I will spend some time to discuss ROC curve construction, and interpretation. Consider the dataset we’ve been using last week, > db = read.table("http://freakonometrics.free.fr/db.txt",header=TRUE,sep=";") > attach(db) The first step is to get a model. For instance, a logistic regression, where some factors were merged...

Read more »

eoda’s R-academy celebrates its third anniversary and is extending the extensive training program for R

September 30, 2013
By

The free statistical programming language R becomes more and more popular, even in German speaking areas. This happens for various reasons. Besides from its performance, its quality and its open source character, R scores with its various possibilities for integration. Beyond that R offers a multitude of possibilities in the field of multivariate analysis methods.

Read more »

RcppArmadillo 0.3.920.1

September 30, 2013
By

Along with the Rcpp 0.10.5 release yesterday, a new minor release 0.3.920.1 of RcppArmadillo came out. It is based on Conrad's Armadillo 3.920.0 plus a minor fix, and uses some of the new Rcpp features. Both package is now on CRAN and also in Debian....

Read more »

New version of lme4

September 30, 2013
By

If you haven't realized it yet, a new version of lme4 (version 1.0-4) was released recently (Sept. 21). For an end-user like me, there were not many changes, but there were a few:No more using the @ operator. After a very helpful email exchange with Be...

Read more »

Measuring Randomness in Capital Markets

September 29, 2013
By
Measuring Randomness in Capital Markets

What is Random?As previously discussed, there’s no universal measure of randomness. Randomness implies the lack of pattern and the inability to predict future outcomes. However, The lack of an obvious model doesn’t imply randomness anymore than a curve fit one implies order. So what actually constitutes randomness, how can we quantify it, and why do we care?Randomness $\neq$ Volatility, and Predictability $\neq$ ProfitFirst...

Read more »