HKUST Library Institutional Repository Banner

HKUST Institutional Repository >
Marketing >
MARK Working Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1783.1/830
Title: Data transferability : estimating the response effect of future events based on historical analogy
Authors: Vanhonacker, Wilfried R.
Price, Lydia J.
Keywords: Empirical Bayes estimation
Forecasting
Recursive regression
Issue Date: Jan-1994
Series/Report no.: Marketing Working Paper Series ; MKTG 94.002
Abstract: Many managerial decisions are made with considerable uncertainty about their possible impacts. In assessing such problems, we often rely on analogous situations in the hope that they will shed light on the possible outcomes. This historical analogy assessment is often done in a rather ad hoc fashion. This paper introduces a formal methodology for transferring information or data from one situation to another. A simple recursive least squares approach to the Bayesian data transferability problem is discussed. Focus is on the method's applicability to commonly encountered marketing problems. Empirical testing and estimation issues are discussed and illustrated in the framework of generic substitution of brandname drug sales following patent expiration.
URI: http://hdl.handle.net/1783.1/830
Appears in Collections:MARK Working Papers

Files in This Item:

File Description SizeFormat
mktg94002.pdf3041KbAdobe PDFView/Open

All items in this Repository are protected by copyright, with all rights reserved.