Hi

I'm on the fence about clinical judgment, but definitely on the side of the 
dart board over the stock-brokers, especially for long-term predictions.

http://www.google.ca/url?sa=t&rct=j&q=&esrc=s&frm=1&source=web&cd=2&ved=0CDEQFjAB&url=http%3A%2F%2Fwww.studyfinance.com%2Fjfsd%2Fpdffiles%2Fv8n1%2Fliang.pdf&ei=JGn-UseWJsHtoASb4IEw&usg=AFQjCNGLO4Js3e-KUSF1FI1oU-99ktUyrA&bvm=bv.61535280,d.cGU

Of course, such findings illustrate the problem of coming up with priors.  
Perhaps there is also some element of an infinite regress ... is your evidence 
for the priors built on Bayesian reasoning ... what about the priors for that 
.... and so on.

Take care
Jim

Jim Clark
Professor & Chair of Psychology
204-786-9757
4L41A

From: [email protected] [mailto:[email protected]]
Sent: Friday, February 14, 2014 12:26 PM
To: Teaching in the Psychological Sciences (TIPS)
Subject: RE: [tips] Scientific method: Statistical errors : Nature News & 
Comment

Paul C Bernhardt wrote:

"My only problem with the Bayesian approach, described elegantly in the 
article, is that the posterior probabilities are so dependent on the prior 
probabilities."

To which Chris Green replied:

"I hear this all this time, but I disagree. Even wildly divergent priors 
converge fairly rapidly in the face of the same data. In any case, priors are 
not necessarily reflective of mere "bias." They are often reflective of true 
expertise that has been developed informally in a field. To use a classic 
example, if you want to know what the probability is that two countries will go 
to war over, say, the next decade, do you think it is better to start with the 
base probability that ANY two random countries will go to war, or would you 
rather start with the estimate of people who are already expert in the history, 
cultures, and economies of the two countries in question?"

Or, in a more psychology-related example, if you want to know the probability 
that a particular clinical intervention will be effective with a particular 
psychological disorder, do you think it is better to start with the base 
probability that ANY two random interventions will work, or would you rather 
start with the clinical judgment of therapists in the field? Or, if you want to 
know what the probability is that a particular new hire will be an effective 
employee, do you think it is better to start with the base probability of the 
current success rate of new hires on the job or would you rather start with the 
clinical judgment of personnel directors? :) (I won't stretch it any further 
with reference to monkeys with dart boards and stock brokers.)

I do agree with the points of the article and I plan to include this article in 
my readings for my upper division research class. I will also use it to shape 
the approach I take to these issues in my undergraduate stats classes, although 
I am already careful to explain what "statistical significance" means and 
doesn't mean. As to the cultural entrenchment question, I don't know that it is 
specifically psychological culture in which p-values are used in research. Most 
introductory statistics classes seem to teach it the same way without regard to 
the particular discipline in which statistics will be used (I guess I am 
thinking mostly of biology and medicine and I could be wrong about my 
perception of other sciences that use inferential statistics).

Rick


Dr. Rick Froman, Chair
Division of Humanities and Social Sciences
Professor of Psychology
Box 3519
John Brown University
2000 W. University Siloam Springs, AR  72761
[email protected]<mailto:[email protected]>
(479) 524-7295
http://bit.ly/DrFroman




---

You are currently subscribed to tips as: 
[email protected]<mailto:[email protected]>.

To unsubscribe click here: 
http://fsulist.frostburg.edu/u?id=13251.645f86b5cec4da0a56ffea7a891720c9&n=T&l=tips&o=34210

(It may be necessary to cut and paste the above URL if the line is broken)

or send a blank email to 
leave-34210-13251.645f86b5cec4da0a56ffea7a89172...@fsulist.frostburg.edu<mailto:leave-34210-13251.645f86b5cec4da0a56ffea7a89172...@fsulist.frostburg.edu>







---
You are currently subscribed to tips as: [email protected].
To unsubscribe click here: 
http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=34212
or send a blank email to 
leave-34212-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu

Reply via email to