| GaltonFamilies | R Documentation |
This data set lists the individual observations for 934 children in 205 families on which Galton (1886) based his cross-tabulation.
data(GaltonFamilies)
A data frame with 934 observations on the following 8 variables.
familyfamily ID, a factor with levels 001-204
fatherheight of father
motherheight of mother
midparentHeightmid-parent height, calculated as (father + 1.08*mother)/2
childrennumber of children in this family
childNumnumber of this child within family. Children are listed in decreasing order of height for boys followed by girls
genderchild gender, a factor with levels female male
childHeightheight of child
Galton's notebook lists 963 children in 205 families ranging from 1-15 adult children children. Of these, 29 had non-numeric heights recorded and are not included here.
Families are largely listed in decending order of fathers and mothers height.
Galton's notebook, http://www.medicine.mcgill.ca/epidemiology/hanley/galton/notebook/, transcribed by Beverley Shipley in 2001.
Galton, F. (1886). Regression Towards Mediocrity in Hereditary Stature Journal of the Anthropological Institute, 15, 246-263
Hanley, J. A. (2004). "Transmuting" Women into Men: Galton's Family Data on Human Stature. The American Statistician, 58, 237-243. See: http://www.medicine.mcgill.ca/epidemiology/hanley/galton/ for source materials.
Galton,
PearsonLee
data(GaltonFamilies)
str(GaltonFamilies)
## reproduce Fig 2 in Hanley (2004)
library(car)
scatterplot(childHeight ~ midparentHeight | gender, data=GaltonFamilies,
ellipse=TRUE, levels=0.68, legend.coords=list(x=64, y=78))
# multiply daughters' heights by 1.08
GF1 <- within(GaltonFamilies, {childHeight <- ifelse (gender=="female", 1.08*childHeight, childHeight)} )
scatterplot(childHeight ~ midparentHeight | gender, data=GF1,
ellipse=TRUE, levels=0.68, legend.coords=list(x=64, y=78))
# add 5.2 to daughters' heights
GF2 <- within(GaltonFamilies, {childHeight <- ifelse (gender=="female", childHeight+5.2, childHeight)} )
scatterplot(childHeight ~ midparentHeight | gender, data=GF2,
ellipse=TRUE, levels=0.68, legend.coords=list(x=64, y=78))