NumEvents {biostatUZH}R Documentation

Compute number of events for a survival endpoint

Description

Calculates either the required total number of events or the power.

Usage

NumEvents(HR, sig.level=0.05, power=NULL, n.events=NULL, alloc.ratio=1,
          non.inf.margin=NULL, type="sup", alternative="two.sided")

Arguments

HR

Hazard ratio of experimental group vs. control group.

sig.level

Significance level.

power

Desired power.

n.events

Required total number of events.

alloc.ratio

Allocation ratio: Ratio of the number of patients in the experimental group divided by the number of patients in the control group.

non.inf.margin

Non-inferiority margin.

type

Study type. Either "sup" or "superiority" for superiority studies or "noninf" or "non-inferiority" for non-inferiority studies. Default is "sup".

alternative

In c("one.sided","two.sided"), depending on whether the alternative hypothesis is one- or two-sided.

Value

Returns either the required total number of events or the power.

Author(s)

Uriah Daugaard and Leonhard Held
leonhard.held@uzh.ch

References

Collett, D. (2015). Modelling Survival Data in Medical Research. New York: Chapman and Hall/CRC.

Schoenfeld, D.A. (1983). Sample-Size Formula for the Proportional-Hazards Regression Model. Biometrics, 39, 499–503.

Examples

NumEvents(HR = 0.65, sig.level = 0.05, power = 0.9,
          alloc.ratio = 1, type = "sup", alternative = "two.sided")

[Package biostatUZH version 1.8.0 Index]