Cousineau-Laurencelle's lambda correction for cluster-randomized sampling

Source: R/CousineauLaurencelleLambda.R

The functions CousineauLaurencelleLambda() returns the correction factor for cluster-randomized sampling. This correction is then used in a variety of ways, for example, to get the effective number of participants (in a power study) or to correct a t-test. See (Cousineau and Laurencelle 2016) .

CousineauLaurencelleLambda(paramvector)

Arguments

paramvector

A vector with, in that order, the intra-class correlation r, the number of clusters, then the number of participants in all the clusters.

Value

lambda the correction factor for cluster-randomized sampling.

References

Cousineau D, Laurencelle L (2016). “A Correction Factor for the Impact of Cluster Randomized Sampling and Its Applications.” Psychological Methods, 21, 121 -- 135. doi:10.1037/met0000055 .

Examples

# Example from Cousineau & Laurencelle, 2017, p. 124:
CousineauLaurencelleLambda( c(0.2, 5, 20, 20, 20, 20, 20) )
#> [1] 2.234188
# 2.234188