v1.0 of the “pricesensitivitymeter” R package is now available on CRAN. This version adds a new function
psm_analysis_weighted() which allows to properly deal with weighted data.
As far as I know, this is the first implementation of the van Westendorp Price Sensitivity Meter methodology that accounts for weighting.
The R package uses the infrastructure that is provided by the excellent “survey” package: To use weighted data, it must be set up as a “survey design” object via the
svydesign() function from the “survey” package. The
psm_analysis_weighted() function then takes this object as an input (and lets the “survey” package do all the heavy lifting in the background).
As the infrastructure of the “survey” package is very versatile, this means that users of this new function can use all kinds of survey designs (from simple random sampling to complex multi-stage designs or cluster sampling) and still rely on getting the correctly weighted estimates.
I have also added a new vignette “Using Weighted Data” that should help users setting up their PSM analysis with weighted data.
(Besides weighting, I have made a few tiny adjustments for some edge cases.)