Speeding up agent-based simulations with data frames in R

Posted on April 16, 2011 by gary

In health economics it is common to use agent-based simulations for exploring epidemiological models, prevention policies, and clinical interventions, among other things. In C++ I enjoy using object-oriented design to build these agent-based models. It feels so natural. In R, however, I have yet to delve into the S4 object model, and so have instead resorted to using data frames for simple object data structures. Stochastic, agent-based models often require large cohorts and multiple trials, so finding improvements in speed is a great help. The examples listed below are inspired by comments made recently on the r-help list, to whose contributors I am very grateful.

Continue reading →

Posted in Modeling, R | Tagged , , | 13 Comments

Using R and clinical heuristics to explore the Heritage Health Prize: what do we gain?

Posted on April 13, 2011 by gary

The recent opening of the Heritage Health Prize both represents a milestone and raises a cautionary flag. On the one hand, crowdsourced analytics prizes have never tackled anything so noble (not to discount predicting movie ratings), but on the other hand, are we just looking for nails because we all have hammers?

There is a great introduction to importing and preparing the data set here. What next?

If you were just planning to grind the data set straight through your Weka engine, or simply run an ensemble of 100,000 decision trees (am I allowed to say random forest in my blog?) through your Beowulf cluster, you can stop reading here. If, however, you wonder if an understanding of pathophysiology, epidemiology, and clinical medicine might yield some insight into your approach for analytics in this competition, read on.

Continue reading →

Posted in Health, Medicine, R | Tagged , , | 5 Comments

The structure of twitter participant relationships in conversations around #Libya, #Bieber, and #Rstats

Posted on April 4, 2011 by gary

I am a recent comer to twitter, and it took me a few weeks to figure out what this was all about. Who are all these people tweeting each other and what do all these trending hashtags mean? Do these people all know each other? How do they get involved in these conversations? Are people really talking/listening to each other, or just spewing 140 character projectiles out into the void?

This piqued my interest in the structure of relationships of participants in different twitter conversations. Using R, with the twitteR and igraph packages, I wondered what I would find…

Continue reading →

Posted in R, Social Networks, twitter | Tagged , , , , | 4 Comments

Grey’s Anatomy Network of Sexual Relations

Posted on March 25, 2011 by gary

This all began with an introductory presentation about social network analysis to a group of medical students.  What better way to grab their attention than with attractive, fake doctors having sex on television?  Naturally this led to the dense network of sexual contacts between characters on the Grey’s Anatomy television show.  After viewing many hours of previous episodes and exploring fan pages (especially here for an early attempt at a graph representation of sexual contacts), I was able to come up with an extensive but by no means exhaustive list of contacts.  The edge list is available here.

This example uses the igraph package for R, both free to download. First we create the graph, give it a layout, and plot.

Continue reading →

Posted in Health, R, Social Networks | Tagged , , , , | 10 Comments