TeachingDemos (version 2.10)

stork: Neyman's Stork data

Description

Data invented by Neyman to look at spurious correlations and adjusting for lurking variables by looking at the relationship between storks and biths.

Usage

data(stork)

Format

A data frame with 54 observations on the following 6 variables.

County

ID of county

Women

Number of Women (*10,000)

No.storks

Number of Storks sighted

No.babies

Number of Babies Born

Stork.rate

Storks per 10,000 women (=No.storks/Women)

Birth.rate

Babies per 10,000 women (=No.babies/Women)

Details

This is an entertaining example to show a relationship that is due to a third possibly lurking variable. The source paper shows how completely different relationships can be found by mis-analyzing the data.

References

Neyman, J. (1952) Lectures and Conferences on Mathematical Statistics and Probability, 2nd edn, pp. 143-154. Washington DC: US Department of Agriculture.

Examples

# NOT RUN {
data(stork)
pairs(stork[,-1], panel=panel.smooth)
## maybe str(stork) ; plot(stork) ...
# }