« Worklife survey | Main | Fascinating talk by Hans Rosling »
August 07, 2006
Pooling of data
Some good news:
The Bill and Melinda Gates Foundation, run by the chairman of the Microsoft Corporation, will deliver $287 million in five-year grants to researchers working to produce an AIDS vaccine. The caveat: Grantees must agree to pool their results. Fragmented and overlapping work in the area of AIDS research has hindered progress toward a vaccination for the virus that affects 40 million people around the world.... A web site will share data in real time.
More at The Wall Street Journal and at YaleGlobalOnline.
Hopefully this will push the work towards my vision of the interactive analysis of data through the internet instead of the current model of only publishing the not-always-reproducible results of the analysis. See my previous postings on statistical data.
Posted by Aleks at August 7, 2006 12:22 PM
Trackback Pings
TrackBack URL for this entry:
http://www.stat.columbia.edu/~cook/movabletype/mt-tb.cgi/556
Comments
Surely you don't want to pool the data: you want to build a hierarchical model instead.
Eh? Oh.
Bob
Posted by: Bob O'H at August 7, 2006 01:15 PM
Thanks to Bob for the pun :)
Posted by: Aleks ![[TypeKey Profile Page]](../assets/877f66dc64771560.gif)
at August 8, 2006 09:40 AM
Aleks,
You write of "the not-always-reproducible results". In economics, where I have done much research on this idea, it turns out the reproducible results are the exception and not the rule.
Even if you have the data, the article cannot
descibe everything that was done to the data.
Only the actual code can do that. In fact, one
can argue (as Claerbout has done) that the article
often is only the advertisement for the data and
code that underly the published results.
All stats journals (and economics journals) should
have such mandatory data/code archives.
Bruce
Posted by: Bruce McCullough at August 8, 2006 11:47 AM
i'm with bruce re: the paper is meaningless without the raw data and the code that massaged it. bruce please could you post a reference to claerbout's writing on this (or any other relevant materials?)
Posted by: bob at August 12, 2006 07:52 AM