IndexNumR (version 0.6.0)

relativeDissimilarity: Computes measures of relative dissimilarity between all periods

Description

A function to compute the relative price dissimilarity between two vectors of prices.

Usage

relativeDissimilarity(
  x,
  pvar,
  qvar,
  pervar,
  prodID,
  indexMethod = "fisher",
  similarityMethod = "logquadratic"
)

Value

A matrix of dissimilarity measures. The first two columns are the possible combinations of bilateral comparisons and the third column is the dissimilarity measure.

Arguments

x

A dataframe containing price, quantities, a time period index and a product identifier.

pvar

A string identifying the price variable.

qvar

A string identifying the quantity variable.

pervar

A string identifying the time index variable.

prodID

A string identifying the product ID.

indexMethod

A string identifying the index method to use in the calculation. Not relevant for similarityMethod = PLSpread. Supported methods are fisher and tornqvist. Default is Fisher.

similarityMethod

A string specifying the formula for calculating the relative dissimilarity. Valid options are logquadratic, asymplinear, PLSpread and predictedshare. Default is logquadratic.

References

Diewert, W.E. (2002). "Similarity and Dissimilarity Indexes: An Axiomatic Approach" Discussion Paper No. 0210, Department of Economics, University of British Columbia.

Examples

# estimate the dissimilarity between periods in the CES_sigma_2 dataset
# using the log quadratic measure of dissimilarity
relativeDissimilarity(CES_sigma_2, pvar = "prices", qvar="quantities",
pervar = "time", prodID = "prodID", indexMethod="fisher",
similarityMethod = "logquadratic")