BTYDplus (version 0.7.0)

abe.mcmc.DrawParameters: HB Pareto/NBD variant as described in Abe (2009)

Description

Returns 2-element list level_1: 3-dim array [draw x parameter x cust] wrapped as coda::mcmc.list object level_2: 2-dim array [draw x parameter] wrapped as coda::mcmc.list object

Usage

abe.mcmc.DrawParameters(cal.cbs, covariates = c(), mcmc = 1500,
  burnin = 500, thin = 50, chains = 2, mc.cores = NULL, trace = 100)

Arguments

cal.cbs

data.frame with columns x, t.x, T.cal

covariates

list of column names containing customer-level covariates

mcmc

number of MCMC steps

burnin

number of initial MCMC steps which are discarded

thin

only every thin-th MCMC step will be returned

chains

number of MCMC chains to be run

mc.cores

number of cores to use in parallel (Unix only); defaults to min(chains, detectCores())

trace

print logging step every trace iteration

Value

2-element list:

• level_1list of mcmc.list objects; one for each customer, containing individual-level draws

• level_2mcmc.list object containing draws of heterogeneity parameters

References

Abe, Makoto. 'Counting your customers one by one: A hierarchical Bayes extension to the Pareto/NBD model.' Marketing Science 28.3 (2009): 541-553.

See Also

link{abe.GenerateData} mcmc.PAlive mcmc.DrawFutureTransactions