CHAPTER 24 Ten Distributions Worth Knowing 353
The Normal Distribution
The most popular and widely-used distribution is the normal distribution (also
called the Gaussian distribution and the probability bell curve). It describes variables
whose fluctuations are the combined result of many independent causes.
Figure 24-2 shows the shape of the normal distribution for various values of the
mean and standard deviation. Many other distributions (binomial, Poisson,
Student t, chi-square, Fisher F) become nearly normal-shaped for large samples.
The Microsoft Excel statement NORMSINV RAND
(
()) generates a normally
distributed random number, with mean 0 and SD 1.
The Log-Normal Distribution
This distribution is also called skewed. If a set of numbers is log-normally distrib-
uted, then the logarithms of those numbers will be normally distributed (see the
preceding section “The normal distribution”). Laboratory values such as enzyme
and antibody concentrations are often log-normally distributed. Hospital lengths
of stay, charges, and costs are also approximately log-normal.
You should suspect log-normality if the standard deviation of a set of numbers is
so big it’s in the ballpark of the size of the mean. Figure 24-3 shows the relation-
ship between the normal and log-normal distributions.
If a set of log-normal numbers has a mean A and standard deviation D, then the
natural logarithms of those numbers will have a standard deviation
s
Log
D
A
1
2
/
, and a mean m
Log A
s
2
2
/
.
FIGURE 24-2:
The normal
distribution at
various means
and standard
deviations.
© John Wiley & Sons, Inc.