I gave a talk at the Interface Symposium on reproducible research in practice. I went first in the session, so the slides have a bit more background and philosophy. It was a great session; one of Jon Claerbout's colleagues spoke, Sergey Fomel, a founding author of Madagascar; Sorin Mitran from UNC Chapel Hill talked about
An earlier post (1216) introduced a compatibility study (i.e. reverse engineering) of the sas7bdat database file format. The code and documentation for this are here: http://github.com/biostatmatt/sas7bdat. I've recently restructured the code as an R package, and added some functionality. Look for the sas7bdat package on the CRAN. Also, the read.sas7bdat code has been ported to
Just got an email linking to Reproducible Research: A Range of Response, in the new journal Statistics, Politics, and Policy 2(1) by David Banks, who is also the journal's editor. Interestingly, the commentary doesn't mention the journal's policy (if one exists) on the reproducibility of research submitted there. Banks' writing is easy to read, though
In preparation for a talk, I updated Knuth's original diagram in Donald E. Knuth. Literate programming. The Computer Journal, 27(2):97–111, May 1984. The new diagram is Sweave specific. Click the Sweave diagram for a PDF version, or right-click and select 'save image as' for the PNG version. Permission is granted for any use of the
I wrote this post months ago but never hit 'Publish'. But, the subject has changed little since then. So, here's to cleaning out the draft folder... R's connections are the heart of data/code/text input and output. Without connections, R would be crippled. Additional connections make R more ... connected with potential data sources and output
Gompertz Model Visualization # Gomperz growth function gomp <- function(x, a, b, k) a*exp(-b*exp(-k*x)) # Normal model with Gompertz mean function likelihood <- function(weight, age, sigma, a, b, k) { mu <- gomp(age, a, b, k) dnorm(weight, mu, sigma) } # Visualize the model visualize <- function(phi=40, theta=-35) { weight <- seq(0, 250,
This post describes some preliminary results from a compatibility study of the SAS sas7bdat file format. The most current results stored in a github repository here: sas7bdat The ultimate goal is a native solution to the incompatibility between open-source statistical software (e.g. R) and sas7bdat database files. Demonstration There has been significant progress in interpreting
It's been a year since I began keeping a web log. This post presents some thoughts related to the experience. Blogging is Sharing Ideas Blogging is online self-publishing. There is no faster way to share your ideas so broadly. Last year at the useR! conference (in Gaithersburg, MD, just a few months after I started
A recent R-help post asks for examples of Sweave use for web appliations. I think there is very little out there; maybe nothing. Below is a proof of concept for web-based Sweave-ing with rApache. But, it will soon be possible to do this with R's built-in web server. The idea was to treat an Sweave
These graphics look familiar. From the Tor Metrics Portal: "The metrics website uses R to generate custom graphs on demand." See more here: http://metrics.torproject.org/graphs.html.
Zero Inflated Models and Generalized Linear Mixed Models with R.
Zuur, Saveliev, Ieno (2012).
