The Essentials of Biostatistics for Physicians, Nurses, and Clinicians

34

The Essentials of Biostatistics for Physicians, Nurses, and Clinicians,
First Edition. Michael R. Chernick.
© 2011 John Wiley & Sons, Inc. Published 2011 by John Wiley & Sons, Inc.

CHAPTER 3

Graphics and

Summary Statistics

3.1 CONTINUOUS AND DISCRETE DATA

Numerical or quantitative data can be continuous or discrete. Discrete

data are data that consist of a fi nite or a countably infi nite (mathemati-

cally equivalent to the integers) set of numbers. The binomial distribu-

tion that counts the number of successes is a discrete distribution with

a fi nite number of outcomes 0 to n successes out of n. In contrast, the

Poisson distribution counts the number of events occurring in a unit

time interval. It can take on any integer value that is nonnegative. So

it has a countably infi nite set of values for the probability distribution.

A property of discrete data is that between any two values, there are

real numbers that are not possible data points.

On the other hand, continuous data have the property that there

exist two real numbers that are possible values, and any real number

between those numbers is a possible data point. Data that are continu-

ous include such things as weight, volume, area, and density. Although

height and weight are considered continuous, they are usually measured

on a discrete scale, such as inches and pounds respectively.

We call these data continuous because although we can only

measure height to the nearest inch, say, in theory, a person could have

a height between two units of measurement. Practically speaking, if the