II.
Why is the normal distribution useful?
•
Many things actually are norm
a
lly distributed, or very close to it. For exam
ple, height
and intelligence are approxim
a
tely norm
a
lly distributed; m
easurem
ent errors also of
ten
have a norm
a
l distribution
•
The norm
a
l distribution is easy to work with m
a
them
atically. In m
a
ny practical cases,
the m
e
thods developed using norm
a
l theory work quite well even when the distribution is
not norm
al.
•
There is a very strong connection between the size of a sam
p
le N and the extent to which
a sam
p
ling distribution approaches the norm
a
l form
. Many sam
p
ling distributions based
on large N can be approxim
a
ted by the norm
a
l distribution even though the population
distribution itself is definitely not norm
a
l.