On this R-data statistics page, you will find information about the Pyx data set which pertains to Trial of the Pyx. The Pyx data set is found in the HistData R package. You can load the Pyx data set in R by issuing the following command at the console data("Pyx"). This will load the data into a variable called Pyx. If R says the Pyx data set is not found, you can try installing the package by issuing this command install.packages("HistData") and then attempt to reload the data. If you need to download R, you can go to the R project website. You can download a CSV (comma separated values) version of the Pyx R data set. The size of this file is about 2,373 bytes.

Trial of the Pyx

Description

Stigler (1997, 1999) recounts the history of one of the oldest continuous schemes of sampling inspection carried out by the Royal Mint in London for about eight centuries. The Trial of the Pyx was the final, ceremonial stage in a process designed to ensure that the weight and quality of gold and silver coins from the mint met the standards for coinage.

At regular intervals, coins would be taken from production and deposited into a box called the Pyx. When a Trial of the Pyx was called, the contents of the Pyx would be counted, weighed and assayed for content, and the results would be compared with the standard set for the Royal Mint.

The data frame Pyx gives the results for the year 1848 (Great Britain, 1848) in which 10,000 gold sovereigns were assayed. The coins in each bag were classified according to the deviation from the standard content of gold for each coin, called the Remedy, R = 123 * (12/5760) = .25625, in grains, for a single sovereign.

Usage

data(Pyx)

Format

A frequency data frame with 72 observations on the following 4 variables giving the distribution of 10,000 soverigns, classified according to the Bags in which they were collected and the Deviation from the standard weight.

Bags

an ordered factor with levels 1 and 2 < 3 < 4 < 5 < 6 < 7 < 8 < 9 < 10

Group

an ordered factor with levels below std < near std < above std

Deviation

an ordered factor with levels Below -R < (-R to -.2) < (-.2 to -.l) < (-.1 to 0) < (0 to .l) < (.1 to .2) < (.2 to R) < Above R

count

number of soverigns

Details

Bags 1-4 were selected as "near to standard", bags 5-7 as below standard, bags 8-10 as above standard. This classification is reflected in Group.

Source

Stigler, S. M. (1999). Statistics on the Table. Cambridge, MA: Harvard University Press, table 21.1.

References

Great Britain (1848). "Report of the Commissioners Appointed to Inquire into the Constitution, Management and Expense of the Royal Mint." In Vol 28 of House Documents for 1849.

Stigler, S. M. (1997). Eight Centuries of Sampling Inspection: The Trial of the Pyx Journal of the American Statistical Association, 72(359), 493-500

Examples

data(Pyx)
# display as table
xtabs(count ~ Bags+Deviation, data=Pyx)

--

Dataset imported from https://www.r-project.org.