Martin,
That's fine as long as you make a good case for why you think plotting
predicted values (alongside some uncertainty measure) is not informative
here. If you come up with an alternative (like the predicted probability of
failure or so) please clearly state what you did and why you think this is
better in this case.
Hth,
Jens
-----Original Message-----
From: gov2001-l-bounces at
lists.fas.harvard.edu [mailto:gov2001-l-
bounces at
lists.fas.harvard.edu] On Behalf Of Martin Andersen
Sent: Thursday, March 20, 2008 12:31 AM
To: Gov 2001 List
Subject: [gov2001-l] Predicted values
I'm a little confused by the graph in (e). If I just naively plot the
realizations from a bunch of Bernoulli random varibles, I get rows of
points corresponding to the O-ring failing and it not failing. Thus
the
graph is not very informative. Would it be more appropriate to think
of
the predicted values as part of a Binomial random variable (with trials
fixed), and graphing the number of O-ring failures in that group?
Martin
--
Martin Sparre Andersen, MPH
Harvard University
Program in Health Policy
anders4 at
fas.harvard.edu
martin.andersen at
aya.yale.edu
AIM: AndersenEPH
Community of Science:
http://myprofile.cos.com/msa25cu
_______________________________________________
gov2001-l mailing list
gov2001-l at
lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l