May 02, 2012
Dr. Mullan on Cancer Education
Promoting International Cancer Education: Report from the 2012 European Association for Cancer Education by Patricia Mullan.
Posted by rbrent at 07:53 PM | Comments (0)
May 01, 2012
Next article: Bayesian assessment
Chris Ricketts is in charge of the progress testing at Penninsula medical college in the UK. He's a statistician by training and a pretty conservative one at that. To see him advocate a Bayesian approach to assessment in medical education is no small thing.
Here's an article from 2011 on the topic. It has some math in it which is daunting, but it's not that bad. There is an effort here at UMich to find a way to integrate medical student assessment longitudinally and this might be the right sort of approach to take.
Some questions to ask:
- What are the shortcomings of this approach?
- Is it beneficial to "red flag" students who underperform according to their own trends as opposed to a standards-based model
- Can students game this system? Will students like this system?
- How would it integrate with other schools' assessments when it's Dean's Letter time?
Posted by rbrent at 06:20 AM | Comments (0)
Post Hoc Reasoning
Here's why I'm becoming a Bayesian.
Let's say I collect the winning lottery numbers from the last 10 years. I sped a couple months trying to find some pattern---any pattern---that generates numbers that would have won a few times. It's even possible I might come up with a model that is statistically significant and accounts for some decent percentage of the variance in lottery numbers.
Have I found a way to predict future lottery draws? Will it make me rich? Why not? But it's statistically significant and predicts an acceptable percentage of variance. Why isn't that enough?
In contrast, if I approach the problem from a Bayesian standpoint, the first thing I have to do is defend the notion that such a model can be made: that is my prior probability and I can't run an analysis without it. In other words, the plausibility of the research is part of the research.
There's a downside to this, of course. If people don't believe a hypothesis is likely to be true, the insightful researcher who suspects it is will have a harder time using a Bayesian approach than a traditional approach.
But that's because Bayesian's don't let you get away with post hoc reasoning. And that's a pretty neat trick.
Posted by rbrent at 06:05 AM | Comments (0)