Two new research areas

As if I didn’t have enough to do (see my previous post), I have two new research topics that I have plans to release papers on this year. I am posting this very brief note for the benefit of my current readers, some of whom may be interested in these topics as well.

The first relates to my new day job. I am now doing technical writing at Electronic Arts, the game company. There is a lot of game-related content in my book, and I have started talking with various folks within EA about submitting papers on game AI and player behavior.

The second relates to my audit consulting, which I still do on weekends. I did considerable consulting work in 2011 with AARM, an audit firm specializing in finding errors in large advertising budgets (like $100 million per year). They have a blog called Marketing Math that talks about some of the technical, professional, and legal issues in their field.

Where our interests overlap is in the field of time reporting. I’m interested in modeling how people spend their time, how time is divided up into tasks for reporting purposes. They’re interested in whether people report their time accurately. The results so far have been very stimulating. For an example of the sort of stuff they do, check out:

Time Keeps Ticking

There will be more on this topic later this year. If you’re interested, please write!


Back in action

Wow, that was a much longer hiatus than I intended. During March I took on a new job, moved to a new apartment, and started a new relationship. It had a predictable impact on my science output.
I am back, still working on footnotes to my book, still posting, still in the game. Thank you for


A very promising discussion

There is an intriguing ‘meeting of the minds’ going on over at Tallbloke’s blog right now. The topic that sparked it was an old controversy from the 19th century, about whether an air column confined to a container would be cooler at the top than at the bottom (because of gravitation).
The fellow who introduced the


Progress on book launch

Despite many distractions and challenges, I have completed making planned cuts to the manuscript of The Decline Effect. (Those who might worry that I’m removing something essential should see my previous post: I’m just going to settle for three graphs on a given topic instead of four.)
Now I’m working on building the final index. It’s


The decline effect gets some press, good and bad

In today’s National Post, there is an interesting piece by Joseph Brean on the subject of spurious statistical correlations in science. It touches briefly on the decline effect, but not in a way that I find entirely encouraging.
Brean cites several papers, including one by Young and Karr on problems with irreproducible results, in the journal


Better news for Tallbloke (Climategate II)

The other day I reported that fellow blogger Tallbloke had had two computers and a router seized by the Norfolk police, as part of the investigation into the Climategate e-mail hack. He was not named as a suspect, just a tenuous link in an evidence chain. There was intense concern among skeptic bloggers over the


Climategate II hits home

A few weeks ago, my ‘Pot Lid’ paper got a favorable mention on Tallbloke’s climate blog. Today I find that acting on a request from the U.S. Department of Justice, a platoon of British policemen descended on Tallbloke’s house and seized several computers.
This isn’t about ‘Pot Lid’. There was another big dump of 5,000 or


More on the decline effect in drug research

There are a number of good articles on the ongoing problems with developing new drugs, but this one leaped out at me. In particular, check out the logarithmic decline in new drugs brought into use per billion $ of research and development funding:

There are some facts not shown in the graph that need to be


The scary truth about audit software blogging

This post is something of an experiment.
As I said in a previous post, I’m interested in knowing just how big the community of expert audit software users is, and where to find them. So I’ve been doing a variety of searches, including setting Google to search only on blogs — that is, on WordPress and


Experimental data uploaded, new page

I have added a page entitled ‘Bayes and decline‘ that will deal with the more technical details of the decline effect. In particular, it will explain why I regard the phenomenon as only explainable using a Bayesian approach.
I’ve also updated the Downloads page by adding an Excel spreadsheet with some probability experiments I ran several