shelltox: Shell Toxicology data

In CorrBin: Nonparametrics with Clustered Binary and Multinomial Data

Description

This is a classical developmental toxicology data set. Pregnant banded Dutch rabbits were treated with one of four levels of a chemical. The actual doses are not known, instead the groups are designated as Control, Low, Medium, and High. Before term the animals were sacrificed, and the total number of fetuses, as well as the number affected by the treatment was recorded.

Usage

data(shelltox)

Format

A 'CBData' object, that is a data frame with the following variables

Trt	factor giving treatment group
ClusterSize	the size of the litter
NResp	the number of affected fetuses
Freq	the number of litters with the given ClusterSize/NResp combination

Source

Paul, S. R. (1982) Analysis of proportions of affected foetuses in teratological experiments. Biometrics, 38, 361-370.

This data set has been analyzed (and listed) in numerous papers, including

Rao, J. N. K. & Scott, A. J. (1992) A Simple Method for the Analysis of Clustered Data. Biometrics, 48, 577-586.

George, E. O. & Kodell, R. L. (1996) Tests of Independence, Treatment Heterogeneity, and Dose-Related Trend With Exchangeable Binary Data. Journal of the American Statistical Association, 91, 1602-1610.

Lee, S. (2003) Analysis of the Binary Littermate Data in the One-Way Layout. Biometrical Journal, 45, 195-206.

Examples

  data(shelltox)
  stripchart(I(NResp/ClusterSize)~Trt, cex=sqrt(shelltox$Freq), data=shelltox, pch=1, 
             method="jitter", vertical=TRUE, ylab="Proportion affected")

Example output

CorrBin documentation built on May 2, 2019, 4:46 p.m.