Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sun-barr!olivea!oliveb!veritas!amdcad!amdcad!military
From: prentice%triton.unm.edu@ariel.unm.edu (John Prentice)
Newsgroups: sci.military
Subject: Re: How effective was the Stealth fighter?
Message-ID: <1991Apr18.032708.22238@amd.com>
Date: 17 Apr 91 22:15:49 GMT
References: <1991Apr9.025945.1283@amd.com> <1991Apr11.033856.5300@amd.com> <1991Apr17.055319.13285@amd.com>
Sender: military@amd.com
Organization: University of New Mexico, Albuquerque, NM
Lines: 24
Approved: military@amd.com


From: prentice%triton.unm.edu@ariel.unm.edu (John Prentice)


stevenp@decwrl.pa.dec.com (Steven Philipson) writes:
>   The loss rates of all aircraft were low, but I haven't seen any
>official statement that the *difference* in loss rates between were
>statistically insignificant.  A large number of sorties and flight
>hours were recorded.  Reported losses as I've seen them seem to indicate
>that the rates *are* significantly different.  Could you please tell us
>why you conclude that they are not?

Look at the standard deviation for the number of combat
sorties flown.  In simple terms, if N were flown, a one sigma
deviation is the square root of N.  There were far fewer planes
lost that this, so the loss rate for Stealth was within a one
sigma deviation of the loss rate for everything else.  You should
be careful to take out mechanical failures in this analysis also,
though it won't change the results any.

-- 
John K. Prentice    john@unmfys.unm.edu (Internet)
Dept. of Physics and Astronomy, University of New Mexico, Albuquerque, NM, USA
Computational Physics Group, Amparo Corporation, Albuquerque, NM, USA