DEC 7, 2010 10:31am ET

Related Links

Yahoo Said to Buy Analytics Company Flurry
July 22, 2014
Gartner: ‘Cognizant Computing’ to Become a Force in Consumer IT
July 21, 2014
Ex-Merrill Lynch Banker Uses Big Data to Save Pubs
July 21, 2014

Web Seminars

How Customer Analytics Can Lower Costs and Raise Revenue
July 29, 2014
Improve Omni-channel Shopping Experience with Product Information Management
August 21, 2014

Bayes and Risk Management – Part 2

Print
Reprints
Email

Last week's blog introduced Bayes theorem for conditional probability and contrasted the Bayesian and frequentist approaches in modern statistics, noting that the frequentist camp dominated when I studied 30 years ago. Now, however, though frequentism is still on top, the playing surface is much more level, with a steeper trajectory for Bayes.

Get access to this article and thousands more...

All Information Management articles are archived after 7 days. REGISTER NOW for unlimited access to all recently archived articles, as well as thousands of searchable stories. Registered Members also gain access to:

  • Full access to information-management.com including all searchable archived content
  • Exclusive E-Newsletters delivering the latest headlines to your inbox
  • Access to White Papers, Web Seminars, and Blog Discussions
  • Discounts to upcoming conferences & events
  • Uninterrupted access to all sponsored content, and MORE!

Already Registered?

Advertisement

Comments (2)
Although it has been 30+ years since I took statistics, I had the good fortune (as an undergrad) to have a professor spend a fair amount of time equating if|then to Bayesian statistics. Even though this pre-dated the advent of the personal computer and lots of programming coursed, it struck me as reasonable. It still does.

So, from a perspective of "reasonable", would it be reasonable to assume the "frequentist" model of statistics could be used, over time, to validate the quality of the "priors" used in Bay3sian analysis to at least some degree, thus over time improving the quality of the information and utilizing the best aspects of both analytical approaches? Or should I go back to sleep for another 30+ years?

Thanks for your blogs, I always thoroughly enjoy and appreciate your perspective.

Posted by Gary B | Wednesday, December 08 2010 at 6:07PM ET
Gary --

Please stay awake -- you're absolutely correct!

The evolution from subjective to uninformative priors puts the scientific rigor of frequentistism to work for the Bayesian method. As Brad Efron notes, Empirical Bayes and computational statistics offer much promise for the field.

Regards.

Posted by steve m | Thursday, December 09 2010 at 8:08AM ET
Add Your Comments:
You must be registered to post a comment.
Not Registered?
You must be registered to post a comment. Click here to register.
Already registered? Log in here
Please note you must now log in with your email address and password.
Twitter
Facebook
LinkedIn
Login  |  My Account  |  White Papers  |  Web Seminars  |  Events |  Newsletters |  eBooks
FOLLOW US
Please note you must now log in with your email address and password.