[Jdm-society] Experimenter bias

[McNamara, Laura A]

Hello everyone,

Usually I lurk on this list, but this question came across my e-desk and I wondered if any of you can comment. Feel free to contact Ken off list - he's a physicist at Los Alamos National Laboratory.

Laura 



Laura,

I hope all is going well with you.

I have been thinking about a topic that I believe is right up your
alley, and am wondering whether you can point me in a useful direction.

I have been looking at the historical record of measurements of
fundamental quantities in physics. I believe there is evidence to
support the notion that experimenters may be influenced, perhaps
subconsciously, by previously published results. Those of us who are
or have been involved in physics experiments recognize this
possibility. We realize that there is a definite tendency to question
what you have missed, if your results differs from earlier ones. On
the other hand, it is difficult the get scientists to talk candidly
about this effect.

Incidentally, I have signed up to talk in a few months about what we
can learn about likelihood functions from the history of
nuclear-physics measurements. My main purpose is to determine whether
the data support long-tailed likelihood functions, which are often
invoked to handle outliers.

I am wondering whether you have considered or studied the issue of
experimenter bias toward matching previous results. Is this a topic
that has been addressed by statisticians or elicitation experts, and
if so, what keywords would apply? 


I can imagine that one could even model this effect, to some extent.
The problem is that people handle differences of opinion (measured
results) in various ways. Some would question themselves, others the
previous experimenters. Anyway, it is an interesting topic.

Cheers,
Ken Hanson


MS D413/T-16
Los Alamos National Laboratory
Los Alamos, NM 87545, USA

PHN: 505 662 4370
E-MAIL: kmh at lanl.gov
Group office, PHN: 505 667 4835, FAX: 505 667 1931
At home: kennethmhanson at msn.com, 505 662 4370
WWW: http://www.lanl.gov/home/kmh




-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.sjdm.org/mail-archive/jdm-society/attachments/20070508/a3728135/attachment-0001.htm