The Normal Distribution

An Illustration of Basic Probability

By Dave Krider

The normal (or Gaussian) distribution is one of the most commonly observed and is the starting point for modeling many natural processes. It usually is found in events that are the aggregation of many smaller, but unobservable events. A good example is the motion of small particles of dust in water. When viewed in a microscope they perpetually move back and forth from the random impacts of water molecules. If one were to plot the distance traveled by dust particles over a given time interval and repeat the measurement several times, the resulting distribution would be normal. The path followed by the dust particles is referred to as Brownian motion. In this case, the movement of the dust is the aggregation of several random shocks from the water molecules.

The exhibit below illustrates a more simple process that gives rise to the familiar "bell curve" of the normal distribution. In this case balls are dropped from the top and pass through a series of pins until they hit the bottom. Once at the bottom, they stack up to record the number that have hit that point. At first there does not seem to be any pattern but after a few minutes the stacks conform to the superimposed curve.

A Java-compatible browser is required to view this.

[Click on applet to stop and start.]

This Applet may be imbedded within your own web page with the following HTML:

<applet code="BallDrop.class" width=300 height=300>
<PARAM NAME="BallImage" VALUE="smallball.gif">
<PARAM NAME="PinImage" VALUE="smallpin.gif">
<PARAM NAME="NumRows" VALUE="8">
<PARAM NAME="NumColumns" VALUE="20">
<PARAM NAME="NumBalls" VALUE="5">
<PARAM NAME="Delay" VALUE="10">
<PARAM NAME="TopSpace" VALUE="30">
<PARAM NAME="SideSpace" VALUE="20">

The original BallDrop applet is Copyright 1995 David Krider, all rights reserved.