CHAPTER 19 Other Useful Kinds of Regression 275

Interpreting the Poisson regression output

After you follow the steps for running a Poisson regression in the preceding

section, the program produces output like that shown in Figure 19-2, which is the

Poisson regression output from R’s generalized linear model function (glm).

This output has the same general structure as the output from other kinds of

regression. The most important parts of it are the following:»

» ^{In the coefficients table (labeled Coefficients:), the estimated regression}

coefficient for Year is 1.3298, indicating that the annual number of fatal

accidents is increasing by an estimated 1.33 accidents per year.»

» ^{The standard error (SE) is labeled Std. Error and is 0.3169, indicating the}

precision of the estimated rate increase per year. From the SE, using the rules

given in Chapter 10, the 95 percent confidence interval (CI) around the

estimated annual increase is approximately 1 3298

1 96

0 3169

.

.

.

x

, which

gives a 95 percent CI of 0.71 to 1.95 (around the estimate 1.33).

FIGURE 19-1:

Yearly data on

fatal highway

accidents

in one city.

© John Wiley & Sons, Inc.

FIGURE 19-2:

Poisson

regression

output.