chl
• Member for 11 years, 5 months
• Last seen this week
• Paris, France

I never used it directly, so I can only share some papers I had and general thoughts about that technique (which mainly address your questions 1 and 3). My general understanding of biclustering ...

To add to @dmk38's response, "any set of scores gives a valid test, provided they are constructed without consulting the results of the experiment. If the set of scores is poor, in that it badly ...

I earlier suggested the recent paper by Friedman and coll., Regularization Paths for Generalized Linear Models via Coordinate Descent, published in the Journal of Statistical Software (2010). Here are ...

For a talk, I've used the following picture which is based on the sleepstudy dataset from the lme4 package. The idea was to illustrate the difference between independent regression fits from subject-...

The most commonly used correlational approach is called multi-trait scaling (MTS). The idea behind MTS is that items belonging to the same dimension are supposed to be more correlated to each other, ...

If you take a look at the code (simple type plot.lm, without parenthesis, or edit(plot.lm) at the R prompt), you'll see that Cook's distances are defined line 44, with the cooks.distance() function. ...

You can use relevel() to change the baseline level of your factor. For instance, > g <- gl(3, 2, labels=letters[1:3]) > g [1] a a b b c c Levels: a b c > relevel(g, "b") [1] a a b b c c ...

Anyone who considers arithmetical methods of producing random digits is, of course, in a state of sin. -- Von Neumann

I would try some kind of 3D heatmap, mosaic plot or a sieve plot (available in the vcd package). Isn't the base mosaicplot() function working with three-way table? (at least mosaic3d() in the vcdExtra ...

It is quite difficult to answer your question in a precise manner, but it seems to me you are comparing two criteria (information criteria and p-value) that don't give the same information. For all ...

I like to think of CIs as some way to escape the Hypothesis Testing (HT) framework, at least the binary decision framework following Neyman's approach, and keep in line with theory of measurement in ...

Ok, I drop a quick response. Your idea is correct in that the regression coefficient is the log of the OR. More precisely, if $b$ is your regression coefficient, $\exp(b)$ is the odds ratio ...

Off the top of my head, I would say that the following general purpose books are rather interesting as a first start: Izenman, J. Modern Multivariate Statistical Techniques: Regression, ...

Here are some online ressources I found interesting without going into detail (and I'm not a specialist of this topic): Hierarchical Dirichlet Processes, by Teh et al. (2005) Dirichlet Processes A ...

A few thoughts: (a) Use transparency, and (b) Allow for some interactivity. Here is my take, largely inspired by a Java applet on Type I and Type II Errors - Making Mistakes in the Justice System. As ...

There are various packages for representing directed and undirected graphs, incidence/adjacency matrix, etc. in addition to graph; look for example at the gR Task view. For visualization and basic ...

A boxplot isn't that complicated. After all, you just need to compute the three quartiles, and the min and max which define the range; a subtlety arises when we want to draw the whiskers and various ...

Definitively Econometric Analysis, by Greene. I'm not an econometrician, but I found this book very useful and well written.

I just drop some references about data dredging and clinical studies for the interested reader. This is intended to extend @onestop's fine answer. I tried to avoid articles focusing only on multiple ...

There are also those projects initiated by the FSF or redistributed under GNU General Public License, like: PSPP, which aims to be a free alternative to SPSS GRETL, mostly dedicated to regression and ...

Clason & Dormody discussed the issue of statistical testing for Likert items (Analyzing data measured by individual Likert-type items). I think that a bootstrapped test is ok when the two ...

The idea underlying the k-means algorithm is to try to find clusters that minimize the within-cluster variance (or up to a constant the corresponding sum of squares or SS), which amounts to maximize ...

I met Laura Trinchera who contributed a nice R package for PLS-path modeling, plspm. It includes several graphical output for various kind of 2- and k-block data structures. I just discovered the ...

The low birth weight study This is one of the datasets in Hosmer and Lemeshow's textbook on Applied Logistic Regression (2000, Wiley, 2nd ed.). The goal of this prospective study was to identify risk ...

Introduction to Machine Learning, by E. Alpaydin (MIT Press, 2010, 2nd ed.), covers a lot of topics with nice illustrations (much like Bishop's Pattern Recognition and Machine Learning). In addition,...

In addition to the package that @robin pointed too, you should look at the Spatial Task View on CRAN. What you are describing is known as a choropleth map, as illustrated here: Choropleth Maps of ...

Apart from Protovis (HTML+JS) or Mayavi (Python), I would recommend Processing which is an open source programming language and environment for people who want to create images, animations, and ...

The Elements of Statistical Learning, by Hastie et al. has a lot of illustrations of Machine Learning applications, and all data sets are available on the companion website, including data on spam as ...