BasicElectionForensics: Basic Election Forensics function

In kkalininMI/EFToolkit: Election Forensics Toolkit

Description

This function helps to run basic election forensics methods: Benford's 2nd Digit, Last Digit (Counts), Counts (05s), Multimodality Test, Sobyanin-Sukhovolsky test and Correlation test.

Usage

BasicElectionForensics(data, Candidates, Level,
                             TotalReg, TotalVotes, Methods, R=1000, cores=2)

Arguments

data	data frame
Candidates	variable name referring to vote counts for candidates/parties
Level	variable name depicting the level of analysis ("National", i.e. whole dataset by default)
TotalReg	variable name for the total number of eligible voters
TotalVotes	variable name for the total number of ballots cast
Methods	"_2BL" - second-digit mean test (to be compared to the mean value Benford's Law) "LastC" - last-digit mean test (to be compared to the mean value implied by uniformly distributed last digits) "P05s" - percentage last-digit 0/5 indicator mean (to be compared to the mean value implied by uniformly distributed percentages) "C05s" - count last-digit 0/5 indicator mean count (last-digit 0/5 indicator mean) "Sobyanin" - Sobynin-Sukhovolsky measure "Skew" - skewness (the extent to which a variable departs from a normal distribution by being asymmetric) "Kurt" - Kurt (the extent to which a variable departs from a normal distribution by being spread out too much or not enough) "DipT" - Unimodality test (tests whether the distribution of a variable departs from unimodality) "Correlation" - correlation coefficient between turnout and vote share
R	number of simulations (1000 simulations by default)
cores	number of cores for parallel computing (2 cores by default)

Value

A list with the following parameters:

• table - dataframe with results

• html - html table with results

• tex - tex table with results

• sigMatrix - significance matrix

Examples

library(EFToolkit)

dat<-read.csv(system.file("Albania2013.csv", package="EFToolkit"))

#NB! R=100 to speed up computations for this example.
eldata<-BasicElectionForensics(dat,
                          Candidates=c("C035", "C050"),
                          Level="Prefectures", TotalReg="Registered",
                          TotalVotes="Ballots",
                          Methods=c("P05s", "C05s", "_2BL", "Sobyanin",
                         "DipT", "Skew", "Kurt", "Correlation"), cores=2, R=100)
eldata

kkalininMI/EFToolkit documentation built on Oct. 28, 2020, 1:47 a.m.