Extreme Observations
Michael Godin Arlotto (154aamga@pic.ucla.edu)
Thu, 30 Nov 95 17:54:03 -0800
This is in responce to Mallory Ham's entry. The 68-95-99% rule states that 68%
of the data fall within one standard deviation, 95% fall within two standard
deviations, and 99% fall within three. So when you consider there is 1% chance
of a pregnancy being three standard deviations or greater away from the mean
(314 days) you are making several wrong assumptions. First of all this rule
only applies to normal distributions with N(0,1). So, in order to use this
rule you must normalize the given data, N(266,16^2). Secondly, the rule states
that 99% of the data is three or more standard deviations away from the mean in
either direction. This simply states (mean + 3 s.d.'s) and (mean - 3 s.d.'s)
or or in other words if we let x=the length of the pregnancy, then x<218 or
x>314. We are only concerned with the upper critical value.
If you use the normalize the data, then you will see that
P(x>310)=.003.
So there is a 3/1000 chance of a pregnancy of this length simply by chance.
I'll talk to ya soon,
Mike
Back to the Chatroom Homepage...
Back to the Stats 154A Homepage...
Back to the listings...
Send a message...
This archive was generated by hypermail 1.02.