power_Poisson {PASSED}

Power Calculations for Test of Two Poisson Ratios

Description

Compute the power for a test of two sample means with Poisson distributions, or determine parameters to obtain a target power.

Usage

power_Poisson(n1 = NULL, n2 = NULL, power = NULL, sig.level = 0.05,
lambda1 = NULL, lambda2 = NULL, t1 = 1, t2 = 1, RR0 = 1,
equal.sample = TRUE, alternative = c("two.sided", "one.sided"))

Arguments

n1

sample size in group 1, or sample size in each group if equal.sample = TRUE

n2

sample size in group 2

power

power of test (1 minus Type II error probability)

sig.level

significance level (Type I error probability)

lambda1

Poisson rate for group 1

lambda2

Poisson rate for group 2

t1

observed time period for group 1

t2

observed time period for group 2

RR0

the ratio of lambda2 and lambda1 under null hypothesis

equal.sample

equal sample sizes for two groups, see details

alternative

one- or two-sided test

Details

Exactly one of the parameters n1, n2, lambda1, lambda2, power, and sig.level must be passed as NULL, and that parameter is determined from the others. Notice that sig.level has non-NULL defaults, so NULL must be explicitly passed if you want to compute them.

If equal.sample = TRUE is used, n2 would be ignored and N in output denotes the number in each group.

Value

Object of class "power.htest", a list of the arguments (including the computed one) augmented with method element.

Note

'uniroot' is used to solve power equation for unknowns, so you may see errors from it, notably about inability to bracket the root when invalid arguments are given.

References

Gu et al. (2008). Testing the ratio of two poisson rates. Biometrical Journal: Journal of Mathematical Methods in Biosciences. 50:283-298.

Examples

# Calculate power, equal sizes
power_Poisson(lambda1 = 0.0005, lambda2 = 0.003, n1 = 2000, t1 = 2, t2 = 2)
# Calculate sample size, equal sizes
power_Poisson(lambda1 = 0.0005, lambda2 = 0.003, power = 0.8, t1 = 2, t2 = 2)
# Calculate sample size for group 2, unequal sizes
power_Poisson(n1 = 2000, lambda1 = 0.0005, lambda2 = 0.003, power = 0.8, 
t1 = 2, t2 = 2, equal.sample = FALSE)