A simulated dataset giving the number of infections recorded for 100 patients over a one-year follow-up in a placebo-controlled study. It is designed for teaching Poisson regression of a count outcome on a treatment group and a continuous covariate.
data("infections")A data frame with 100 rows and 4 columns.
patient identifier (1 to 100).
the treatment group, "placebo" or "treated".
the patient's age, in years.
the number of infections recorded during the one-year follow-up (a count outcome).
A simulated dataset created for teaching Poisson regression. The counts
were generated as count ~ Poisson(mu) with
log(mu) = 1.6 - 0.8 * (treatment == "treated") + 0.25 * ((age - 40) / 10)
(see data-raw/infections.R), so the treated group has a lower infection
rate.
data(infections)
head(infections)
#> id treatment age count
#> 1 1 placebo 32 4
#> 2 2 placebo 52 5
#> 3 3 placebo 36 4
#> 4 4 placebo 55 12
#> 5 5 placebo 58 7
#> 6 6 placebo 22 5
# Poisson regression of the infection count on treatment and age
fit <- glm(count ~ treatment + age, family = poisson, data = infections)
summary(fit)
#>
#> Call:
#> glm(formula = count ~ treatment + age, family = poisson, data = infections)
#>
#> Coefficients:
#> Estimate Std. Error z value Pr(>|z|)
#> (Intercept) 0.668071 0.210448 3.175 0.0015 **
#> treatmenttreated -0.831754 0.112840 -7.371 1.69e-13 ***
#> age 0.023955 0.004568 5.244 1.57e-07 ***
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#>
#> (Dispersion parameter for poisson family taken to be 1)
#>
#> Null deviance: 171.273 on 99 degrees of freedom
#> Residual deviance: 75.838 on 97 degrees of freedom
#> AIC: 383.19
#>
#> Number of Fisher Scoring iterations: 4
#>