survcomp (version 1.22.0)

test.hetero.est: Function to test the heterogeneity of set of probabilities

Description

The function tests whether a set of p-values are heterogeneous.

Usage

test.hetero.est(x, x.se, na.rm = FALSE)

Arguments

x

vector of estimates

x.se

vector of standard errors of the corresponding estimates

na.rm

TRUE if the missing values should be removed from the data, FALSE otherwise

Value

Q

Q statistic

p.value

p-value of the heterogeneity test

Details

The heterogeneity test is known to be very conservative. Consider a p-value < 0.1 as significant.

References

Cochrane, W. G. (1954) "The combination of estimates from different experiments", Biometrics, 10, pages 101--129.

See Also

combine.test

Examples

set.seed(12345)
x1 <- rnorm(100, 50, 10) + rnorm(100, 0, 2)
m1 <- mean(x1)
se1 <- sqrt(var(x1))
x2 <- rnorm(100, 75, 15) + rnorm(100, 0, 5)
m2 <- mean(x2)
se2 <- sqrt(var(x2))

test.hetero.est(x=c(m1, m2), x.se=c(se1, se2))