SnedecorCochran {bayesmeta}

Artificial insemination of cows example data

Description

This data set gives means and (squared) standard errors of percentages of conceptions obtained from samples for six bulls.

Usage

data("SnedecorCochran")

Format

The data frame contains the following columns:

no	character	identifier
n	numeric	sample size
mean	numeric	mean
var	numeric	variance (squared standard error)

Details

Quoting from Snedecor and Cochran (1967), Sec. 10.18: “In research on artificial insemination of cows, a series of semen samples from a bull are sent out and tested for their ability to produce conceptions. The following data from a larger set kindly supplied by Dr. G. W. Salisbury, show the percentages of conceptions obtained from the samples for six bulls.”

Source

J. Hartung, G. Knapp, and B.K. Sinha. Statistical meta-analysis with applications. Wiley, Hoboken, NJ, USA, 2008.

References

G.W. Snedecor and W.G. Cochran. Statistical Methods. Iowa State University Press, Ames, IA, USA, 6th edition, 1967.

Examples

data("SnedecorCochran")

## Not run: 
# analyze using uniform prior:
bma1 <- bayesmeta(y=SnedecorCochran[,"mean"],
                  sigma=sqrt(SnedecorCochran[,"var"]),
                  label=SnedecorCochran[,"no"],
                  tau.prior="uniform")

# analyze using Jeffreys prior:
bma2 <- bayesmeta(y=SnedecorCochran[,"mean"],
                  sigma=sqrt(SnedecorCochran[,"var"]),
                  label=SnedecorCochran[,"no"],
                  tau.prior="Jeffreys")

# compare results:
print(bma1)
print(bma2)

forestplot(bma1)
forestplot(bma2)

## End(Not run)