Monday, September 8, 2014


From the NYT:
After the episode, the Ravens said on Twitter: “Janay Rice says she deeply regrets the role that she played the night of the incident.” The tweet was deleted Monday afternoon.
The facts of the case are all old news and the original "consequences" for this to Mr. Rice was a two-game suspension.  The new action (some sort of indefinite suspension) is a result of the public availability of this video.  This is apparently where we're at with the whole feminism/sports hero thing.  

Thursday, July 17, 2014

Tuesday, October 15, 2013

The transcriptome of BRAAAAIIINNNZZZZZ!!!11!

Molecular ecology has a neat, "it's-obvious-once-somebody-does-it" article at the intersection of behavioural ecology and molecular biology by Rey[1] and Boltana.  They took a bunch of zebrafish and separated them into groups (P and R, not sure why).  Then they confirmed their classification by repeating the experiment a while later and applied a series of standard measures of behavioural type (boldness and activity, mostly) and proceeded to mash/freeze fish brains and do some standard stuff to get transcribed mRNA[2] and a transcriptome-style analysis.  There's a lot of FDR-adjusted p-values thrown around about which things were up- or down-regulated, but the figure which highlights low/high expression differences between the groups tells you (almost) everything you need to know.

Rey and Boltana's main finding is that by pre-classifying individuals according to behavioural type they can predict some of the transcriptome variation (9% is their favourite number) and therefore make that data easier to analyze.  For anyone interested in actual animal behaviour the key finding is that you can take pretty crude behavioural measures and expect them to be related to transcription in the brain.  This kind of work gives me some real hope for bringing together neuroscience and movement/behavioural ecology.

[1] I think I got the right character there...
[2] Bonus question to any intro bio students who find this, why the liquid nitrogen?
[3] I must have blogger set to non-US spellings, it keeps complaining about "behavior" and I just comply.

Thursday, June 13, 2013

A readable Boost Graph Library (BGL) tutorial!

The BGL documentation is a little abstract for me so I enjoyed finding this little gem.  Probably even if you don't know French the examples are quite good.

Tuesday, May 7, 2013

tryCatch! Fetch! Roll over! Little R details.

One of the most effective ways of dealing with R's slowness, when the completion of a script is not time-critical, is to start it and walk away.  Most of us have other things going on[1] and it's often fine to come back for your results the later in the day or the week.  While it might be nice to recode an script to run faster, it's often a waste of time. 

One difficulty with this approach is that if you haven't thought through all of your corner cases in a long running script, then you might come back to a script which died five minutes after you left it[2].  This is exacerbated by R's treatment of types which is best described as "loosey goosey" and even errors which you trigger on line #1 will happily propagate, as bogus data, for at least as long as it takes you to leave your desk chair.

That said, catching errors in R is not too hard, especially if you're willing to use awkward-looking constructs like tryCatch.  When I initially read the documentation it wasn't clear to me what signals you can set handlers for, and what you were supposed to do with the expressions, then I wrote the following code based on another example[3]:

N <- 20="" 50="" br="" k="">xs <- data="rnorm(n=N*K)," matrix="" ncol="K)<br" nrow="N,">ys <- data="rnorm(n=N*K)," matrix="" ncol="K)<br" nrow="N,">
o <- br="" list="">for ( i in 1:K ) {
    expr = { 

      if (i==10) stop ("WOOT!") else
        o[[i]] <- br="" i="" lm="" xs="" ys="">    interrupt = function(ex) {
    warning = function(ex) {
    error = function(ex) {
    finally = { cat("Ta-da!\n") }

The expression itself is silly, it's running a series of linear models, but it fails when "i" is 10.  The output is placed into a list and looking at "o" you'll notice that all the models ran, except for the 10th one which returned a NULL instead.  There should be K-1 models with results and K "Ta-da!" messages.  The code in the "finally" argument runs whether an error is caught or not, so you can use it to close file or database handles, or otherwise clean up your mess.  Don't be too tidy because you might clean up evidence for why your code failed. 

The error/warning handlers are pretty self-explanatory---they can be triggered using the "stop"/"warning" commands---but the interrupt handler might not be so obvious.  Interrupts are most commonly sent on my Linux machine in response to a Cntrl-C, and on Windows in response to an Esc.  For debugging it can be nice to put code in there which summarizes the state of your program and presents it to you nicely. 

One surprising thing is that whatever you do in a tryCatch expression is not local---in the above example, the list "o" appears in the global environment.  I might have guessed that, but ?tryCatch says "‘tryCatch’ evaluates its expression argument in a context where the handlers provided in the ‘...’ argument are available." which made me think it had it's own environment like a function.

It won't save you from silly things like forgetting to save your results but it'll save you from some things.

[1] ...meetings to go to, classes to teach, intro sections to write, diapers to change.

[2] It's never happened to me, but I hear it's a common problem.


Friday, May 3, 2013

Filial cannibalism, i.e.- status, sacrifice and workplace relations in the academy

While waiting to see if anaphylaxis was in my near future during a routine doctor's visit, I overhead a conversation between two men.  Nominally it was a professional conversation about past jobs, present opportunities, and the difficulties of the job search.  In reality one was hoping that the other would help him acquire a job and the conversation had gotten a little awkward before the fully-employed gentleman caught on.  Mr. Employed soon started working to gently reduce expectations, but Mr. Hopeful was in a bind because he had to pretend he did not ask about work in the first place to maintain a sense of professional decorum.  Then the conversation generated this gem:

Mr. Employed: "... but we still have to find people to teach X".

Mr. Hopeful, interrupting: "Just hire adjuncts, they're cheap."

Well played Mr. Hopeful, well played.  Good luck with that job search.

Figure 1: Mr. Hopeful prepares for his final job interview and salary negotiations.

Friday, March 22, 2013

Bayesian Versus Frequentist

In 2008 I took a course from Michael Lavine called "Introduction to Statistical Thought".  Beyond delivering the material promised in the title, it also got me hooked on Bayesian inference by making the tools so readily accessible conceptually and technically.  One thing I did not get out of the class was a good understanding of how, in general, one goes about estimating things outside the Bayesian framework.  Cosma Shalizi just fixed that for me, and maybe he could for you too.  Somehow it's much easier for me to think about the technical requirements after seeing this sketch.  I am not sure why this is not part of Michael's class, but I can't repeat the class over and over just to find out if he skipped asymptotic estimation on purpose or by accident*.

* Michael's book (linked above) does have a new section on Asymptotics which was absent when I took the course!