Simpsons (version 0.1.0)

Simpsons-package: Detecting Simpson's Paradox

Description

This package detects instances of Simpson's Paradox in datasets of bivariate continuous data . It examines subpopulations in the data, either user-defined or by means of cluster analysis, to test whether a regression at the level of the group is in the opposite direction at the level of subpopulations.

Details

Package:

Simpsons

Type:

Package

Version:

1.0

Date:

2012-08-17

References

Fraley, C., & Raftery, A. E. (1998a) MCLUST: Software for model-based cluster and discriminant analysis. Department of Statistics, University of Washington: Technical Report No.342.

Fraley, C., & Raftery, A. E. (1998b). How many clusters? Which clustering method? - Answers via model-based cluster analysis. Department of Statistics, University of Washington: Technical Report no. 329.

Kievit, R.A., Frankenhuis, W. & Borsboom, D. (in preparation). Simpson's Paradox in Psychological Science: A Practical Guide.

Simpson, E. H. (1951). The interpretation of interaction in contingency tables. Journal of the Royal Statistical Society, Ser. B, 13, 238-241.

Examples

## Not run: 
# #example 1. Here, we want to regress 'Coffee' on 'Neuroticism', 
# #taking into account possible gender differences. 
# #Simulating 100 males 
# coffeem=rnorm(100,100,15)
# neuroticismm=(coffeem*.8)+rnorm(100,15,8)
# clusterid=rep(1,100)
# males=cbind(coffeem,neuroticismm,clusterid)
# coffeef=rnorm(100,100,15)
# neuroticismf=160+((coffeef*-.8)+rnorm(100,15,8))
# clusterid=rep(2,100)
# females=cbind(coffeef,neuroticismf,clusterid)
# data=data.frame(rbind(males,females))
# colnames(data) <- c("Coffee","Neuroticism","gender")
# 
# example1=Simpsons(Coffee,Neuroticism,clusterid=gender, data=data)
# example1
# 
# ## End(Not run)