SimultConf: Generate Simultaneous Confidence Intervals
In mlespera/BenGood: Assessing Goodness-of-Fit of Data to Benford's Law

Description Usage Arguments Details Value References See Also Examples

SimultConf takes a vector of observed cell frequencies from a multinomial distribution, N, and given significance level α, returns simultaneous confidence intervals for proportions using seven different methods:

Quesenberry and Hurst
Goodman
Bailey angular transformation
Bailey square root transformation
Fitzpatrick and Scott
Sison and Glaz
Univariate approximate Binomial confidence intervals.

1 2	SimultConf(N, method = c("Quesenberry", "Goodman", "BaileyAng", "Baileysqrt", "Fitzpatrick", "Sison", "binomial"), alpha = 0.05)

N

Vector of observed frequencies.

method

The methods for simultaneous confidence intervals for multinomial proportions. This parameter can take on the following values, or a vector containing any combination of these values separated using commas:

'Quesenberry'
'Goodman'
'BaileyAng'
'Baileysqrt'
'Fitzpatrick'
'Sison'
'binomial'

Specifying no method will return all confidence intervals.

alpha

Choose alpha to generate (1-α)% CIs. If unspecified, default is 0.05.

An easy way to check whether your simultaneous confidence intervals generated by SimultConf cover the Benford probabilities is to use SimultBenp.

See Lesperance et. al (2016) for the formulae of each method.

The output is two matrices: a Lower matrix containing the lower bounds, and an Upper matrix containing the upper bounds of the simultaneous confidence intervals using the methods specified by the user. The univariate approximate binomial CIs are always included.

Lesperance M, Reed WJ, Stephens MA, Tsao C, Wilton B (2016) Assessing conformance with Benford's Law: goodness-of-fit tests and simultaneous confidence intervals. PLoS one; 11(3). Wong, S. (2010) Testing Benford's Law with the first two significant digits. University of Victoria, Master's thesis.

SimultBenp