determineBins: Determine Bins

In IQSS/PSI-Library: Differentially Private Statistical Releases for Privacy Preservation

Description

Determine the bins of the histogram based on the inputs from the user

Usage

determineBins(varType, rng, bins, n, nBins, impute, granularity, object)

Arguments

varType	Character, the variable type.
rng	Numeric, a priori estimate of the lower and upper bounds of a variable taking numeric values. Ignored for categorical types. Maybe be null for numeric or integer types, in which case the stability mechanism is used.
bins	Character or numeric, the available bins or levels of a variable. Character for categorical variables, a vector of numbers for numeric variables.
nBins	Integer, the number of bins to release.
impute	Boolean, if true then the mechanism should replace missing values with known values from the data.If false, the mechanism should leave missing values as 'NA'
granularity	Numeric, the width of each histogram bin, or the number of observations in each bin
object	Object, the dpHistogram object for the given variable (used it access and assign variable type)

Details

If the user inputs a list of bins, the input bins will override the data and will be released as the histogram bins. If a given bin does not exist in the data, it will still be released in the result. It is possible that this non-existent bin will still have a count, because it will be an option during data imputation in the call to 'fillmissing()'. If the input list of bins does not include a value that exists in the data, the existing value will be changed to 'NA' in the call to 'censorData()' and will then be imputed as one of the input bins in 'fillMissing()'.

Value

a vector of histogram bins. Character vector for categorical variables. Numeric vector for logical, numeric, and integer variables.

IQSS/PSI-Library documentation built on Feb. 15, 2020, 9:03 p.m.