Exact Poisson tests
Performs an exact test of a simple null hypothesis about the rate parameter in Poisson distribution, or for the ratio between two rate parameters.
poisson.test(x, T = 1, r = 1, alternative = c("two.sided", "less", "greater"), conf.level = 0.95)
- number of events. A vector of length one or two.
- time base for event count. A vector of length one or two.
- hypothesized rate or rate ratio
- indicates the alternative hypothesis and must be
"less". You can specify just the initial letter.
- confidence level for the returned confidence interval.
A list with class
"htest" containing the following components:
"Exact Poisson test"or
"Comparison of Poisson rates"as appropriate.
The rate parameter in Poisson data is often given based on a
“time on test” or similar quantity (person-years, population
size, or expected number of cases from mortality tables). This is the
role of the
T argument. The one-sample case is effectively the binomial test with a very large
n. The two sample case is converted to a binomial test by
conditioning on the total event count, and the rate ratio is directly
related to the odds in that binomial distribution.
### These are paraphrased from data sets in the ISwR package ## SMR, Welsh Nickel workers poisson.test(137, 24.19893) ## eba1977, compare Fredericia to other three cities for ages 55-59 poisson.test(c(11, 6+8+7), c(800, 1083+1050+878))