Answers are grounded in this paper and cite their sources.
Nonprice, nonincome variables are incorporated into a levels version of the Rotterdam model through scaling, translation, combined scaling‐translation and an approach suggested by Theil. In a study of advertising effects on grapefruit and other juice demands, the combined scaling‐translation specification is accepted against an unrestricted specification, while the other specifications are rejected.
No takes yet. Share an insight, caveat, or question.
Mark G. Brown (1994) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: