I’ve been reading about Sequential Monte Carlo recently, and I think it will fit well into the PyMC3 framework. I will give it a try when I have a free minute, but maybe someone else will be inspired to try it first. This paper includes some pseudocode.
Comments Off on Sequential Monte Carlo in PyMC?
Filed under MCMC
A recent IHME seminar by Mark Wheldon described a Bayesian approach to estimating past populations and vital rates by age. I like this stuff. The talk is online, and there is a CSSS working paper on it, too: http://www.csss.washington.edu/Papers/wp117.pdf
Comments Off on IHME Seminar: Bayesian reconstruction: estimating past populations and vital rates by age with uncertainty in a variety of data-quality contexts
Filed under global health, statistics
Last week we read Repeat Bone Mineral Density Screening and Prediction of Hip and Major Osteoporotic Fracture by Berry et al. It argues that repeat screening does not improve predictions. But I think the world needs a better way to measure the quality of predictions like these. Area-under-the-curve doesn’t cut it when you are predicting the unpredictable.
Comments Off on Journal Club: Repeat Bone Mineral Density Screening and Prediction of Hip and Major Osteoporotic Fracture
Filed under global health, statistics
I have added some stylish HTML tooltips to mpld3, make something pretty with them. Demonstration here.
Comments Off on Stylish tooltips in mpld3
Filed under dataviz, software engineering
Software Carpentry has been doing a very interesting project on incorporating code review into the scientific process. The results of the first attempt are here, and the announcement of the second round is here. Maybe you will participate.
Comments Off on Code review in the sciences
Filed under software engineering
One exciting announcement that I got to make at the Verbal Autopsy Congress last October is that the PHMRC gold standard verbal autopsy validation data is now available for all researchers. You can find it in the Global Health Data Exchange: Population Health Metrics Research Consortium Gold Standard Verbal Autopsy Data 2005-2011.
Insert an example of doing something with it here.
Comments Off on Population Health Metrics Research Consortium Gold Standard Verbal Autopsy Data 2005-2011
Filed under global health, machine learning
Our paper comparing the performance of several verbal autopsy (VA) analysis algorithms is now published. This was a long time in the making, so I’m very glad that it is now out in the literature. It is open access, too!
Comments Off on Comparative performance of existing VA methods
Filed under global health, machine learning
Tomorrow is journal club, starting up again for the winter quarter. We are reading Racial Discrimination & Cardiovascular Disease Risk: My Body My Story Study of 1005 US-Born Black and White Community Health Center Participants (US) by Krieger et al.
One exposure paper uses is measured with the Implicit Association Test, which I was trying to explain and couldn’t remember the details of. So I checked online, and learned you can take one yourself! It takes about ten minutes, and may reveal surprising things about you: https://implicit.harvard.edu/implicit/takeatest.html
Comments Off on Journal Club: Racial Discrimination & Cardiovascular Disease Risk
Filed under global health
Tomorrow we have our weekly seminar at IHME, and I’m getting ahead of the curve in mentioning it here. We will hear from Sienna Craig on maternal and child health above 10,000 feet for over 10,000 years. Insert jokes about how that is a long time to be so high. If you are not here in person, you can view the talk online: http://www.healthmetricsandevaluation.org/news-events/seminar/fertility-variation-and-child-survivorship-among-tibetan-women-northern-nepal-bi
Comments Off on IHME Seminar: Sienna Craig on Fertility variation and child survivorship among Tibetan women from northern Nepal
Filed under global health
There is an exciting new project in pythonic interactive data visualization that I have my eye on: mpld3. It plays well with matplotlib-based pretty plotting packages, and has the beginnings of a plugin framework for adding custom interactivity.
I used it to mock up a Cartesian fish eye distortion plot, something I’ve wanted for DisMod-MR ever since I learned about it. (Sometimes the interactivity doesn’t work in that notebook, and requires reloading everything… cutting edge software has some rough edges.)
Filed under dataviz, software engineering
Healthy Algorithms 