Exploring the equivalence of two common mixture models for duration data

Fader, P S, Hardie, B G S, McCarthy, D and Vaidyananathan, R (2019) Exploring the equivalence of two common mixture models for duration data. American Statistican, 73 (3). pp. 288-295. ISSN 0003-1305 OPEN ACCESS


The beta-geometric (BG) distribution and the Pareto distribution of the second kind (P(II)) are two basic models for duration-time data that share some underlying characteristics (i.e., continuous mixtures of memoryless distributions), but differ in two important respects: first, the BG is the natural model to use when the event of interest occurs in discrete time, while the P(II) is the right choice for a continuous-time setting. Second, the underlying mixing distributions (the beta and gamma for the BG and P(II), respectively, are very different—and often believed to be non-comparable with each other. Despite these and other key differences, the two models are strikingly similar in terms of their fit and predictive performance as well as their parameter estimates. We explore this equivalence, both empirically and analytically, and discuss the implications from both a substantive and methodological standpoint.

More Details

Item Type: Article
Subject Areas: Marketing
Additional Information:

This is an Accepted Manuscript of an article published by Taylor & Francis in The American Statistican on 25th March 2019, available online: https://www.tandfonline.com/doi/full/10.1080/00031305.2018.1543134

Date Deposited: 13 Nov 2018 16:07
Date of first compliant deposit: 30 Oct 2018
Subjects: Pareto's law
Last Modified: 21 Jul 2024 01:57
URI: https://lbsresearch.london.edu/id/eprint/1027

Export and Share


Accepted Version - Text


View details on Dimensions' website

Downloads from LBS Research Online

View details

Actions (login required)

Edit Item Edit Item