yolo {elec}R Documentation

Yolo County, CA Election Data

Description

This is for measure W in Yolo County, CA, November 2008. The file includes precinct-level reports.

Usage

data(yolo)

Format

A data frame with 114 observations on the following 8 variables.

PID
Unique identifier for the batches of ballots
Pct
The precinct id of the batch
how
Vote by mail (VBM) or walk-in (PCT)
b
Number of votes cast in that unit
under
Number of undervotes (ballots not voted).
over
Number of overvotes (where someone marked both yes and no).
y
Reported number of valid ballots marked yes.
n
Reported number of valid ballots marked no.

Details

In the actual audit, 6 precincts were selected (see example) and audited by hand-to-eye count by a group of 4 people cross-checking each other. One of the 6 batches had underreported the "yes" votes by 1, and one had overreported the "yes" votes by 1. There were no other errors.

Source

Yolo County, CA. Special thanks to Freddie Oakley and Tom Stanionis.

References

See Stark et al. for papers using this data to illustrate risk-limiting audits of election data.

Examples

# Make an elec.data object out of precicnt-level results
data(yolo)
yolo = make.Z( yolo, C.names=c("y","n","under","over"), tot.votes.col="b" ) 

# Look at different sample sizes and cuts for setting aside
# small precincts
CAST.calc.opt.cut( yolo, beta=0.75, stages=1, t=5, plot=TRUE )

print( yolo )

# Get details of the audit plan -- expected work, etc.
ap <- CAST.calc.sample( yolo, beta=0.75, stages=1, t=5, small.cut=5 )
print( ap )

# Draw a sample (seed not used for actual audit)
CAST.sample(yolo, ap, seed=12345678)


[Package elec version 0.1 Index]