CS395T/CAM383M Computational Statistics  

Go Back   CS395T/CAM383M Computational Statistics > CS395T/CAM383M (Spring 2011) Course Administration > Supplementary Materials

Reply
 
Thread Tools Display Modes
  #1  
Old 02-02-2009, 12:00 PM
wpress wpress is offline
Professor
 
Join Date: Jan 2009
Posts: 222
Default Fun article on Gosset, Fisher, 5% significance, etc.

An economist colleague pointed out to me the attached article about William Gosset, the origin of Student's t, and some other fun historical stuff.

Fisher certainly doesn't emerge as a hero in this retelling, nor do p-value tests!
Attached Images
File Type: pdf jep.22.4 Guinessometrics.pdf (134.5 KB, 1945 views)
Reply With Quote
  #2  
Old 02-09-2009, 03:26 PM
archer archer is offline
Member
 
Join Date: Jan 2009
Posts: 35
Default

if you just can't stop:

biographies of statisticians...


edit: I really like how they tile the photographs...
Reply With Quote
  #3  
Old 05-08-2010, 07:30 PM
johnwoods johnwoods is offline
Member
 
Join Date: Jan 2010
Posts: 30
Default Great article

I really liked this article.

On p. 211, it has a quote from Fisher which I thought was either disingenuous or hyperidealistic:

Quote:
Finally, in inductive inference we introduce no cost functions for faulty judgments...In fact, scientific research is not geared to maximize the profits of any particular organization, but is rather an attempt to improve public knowledge undertaken as an act of faith... We make no attempt to evaluate these consequences, and do not assume that they are capable of evaluation in any currency.
I bolded the part that really bothers me. This statement strikes me as disingenuous. Growing up on Star Trek, I always thought we studied science for the good of humanity -- that humanity is the organization whose profits are (or survival is) maximized by science.

Furthermore, it's unrealistic. I wrote in the margin, while reading, that the statement "itself places a value, however subjective and qualitative, on scientific enterprise." If Fisher thinks science is for the good of public knowledge, then he thinks it has a value. We take this for granted when applying for grants from NIH, NSF, etc., even though those organizations are supposed to promote science for the sake of science.

Worse, Fisher forgets to account for time! You can't get a refund on time. You can license it, but you can't really trade it. In that sense, it's a very valuable commodity, and we favor experiments that maximize statistical certainty while also minimizing time.
Reply With Quote
  #4  
Old 05-10-2010, 08:05 AM
wpress wpress is offline
Professor
 
Join Date: Jan 2009
Posts: 222
Default

Good points. I think that Fisher's stated philosophy of "refusing" to measure things in a common currency is deeply endemic in frequentism, and is its weak point.

Nowadays, maybe because we are ourselves so steeped in market capitalism and under the spell of the economists, we *do* want common currencies. Bayes is of course perfect for that. And so was Gosset.

-B.
Reply With Quote
  #5  
Old 02-01-2011, 11:29 AM
Courtney Courtney is offline
Member
 
Join Date: Jan 2011
Posts: 14
Default Economics and Science

Science, like Art and Exploration, are subject to their benefactors.
Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -6. The time now is 06:48 AM.


Powered by vBulletin® Version 3.8.6
Copyright ©2000 - 2018, Jelsoft Enterprises Ltd.