Model Mis-specification in Newsvendor Decisions: A comparison of Frequentist Parametric, Bayesian Parametric and Nonparametric approaches

32 Pages Posted:

See all articles by Gah‐Yi Ban

Gah‐Yi Ban

London Business School

Zhenyu Gao

Tsinghua University

Fabian Taigel

University of Wuerzburg, Chair of Logistics and Quantitative Methods

Date Written: December 14, 2019

Abstract

Past literature on data-driven inventory models have taken three distinct approaches: Frequentist Parametric (FP), Bayesian Parametric (BP) and Nonparametric. In this paper, we compare across the three approaches for the newsvendor problem. For the two Parametric approaches, we consider both correct and incorrect specifications of the true demand model. We prove, under mild regularity conditions, (i) asymptotic bias and variance formulas of FP and BP are equivalent, (ii) the mis-specified Parametric approaches yield asymptotically biased decisions, unlike the correctly-specified Parametric approaches and the Nonparametric approach, and (iii) asymptotic variance of the mis-specified Parametric approaches converges to zero at rate $1/n$, whereas the rate is $1/n^2$ for the correctly-specified Parametric approaches and the Nonparametric approach. We then show, for nine pairs of assumed versus true demand distribution pairs, (iv) asymptotic bias and variance formulas for all approaches approximate finite-sample bias and variance very well, from $n$ greater than about 50, (v) correctly-specified Parametric approaches dominate the Nonparametric approach in the asymptotic mean-squared error (AMSE) of the decision and the cost, and (vi) surprisingly, it is possible for mis-specified Parametric approaches to dominate the Nonparametric approach in the AMSE of the decision and the cost. We also compare the performance of the three approaches on empirical demand distributions obtained from a large fresh food chain, and find that all methods are viable in a stationary, ``business-as-usual'' setting.

Keywords: data-driven decision-making, newsvendor, inventory, model mis-specification, asymptotic statistics

Suggested Citation

Ban, Gah‐Yi and Gao, Zhenyu and Taigel, Fabian, Model Mis-specification in Newsvendor Decisions: A comparison of Frequentist Parametric, Bayesian Parametric and Nonparametric approaches (December 14, 2019). Available at SSRN: https://ssrn.com/abstract=

Gah‐Yi Ban (Contact Author)

London Business School ( email )

Sussex Place
Regent's Park
London, London NW1 4SA
United Kingdom

Zhenyu Gao

Tsinghua University ( email )

Beijing, 100084
China

Fabian Taigel

University of Wuerzburg, Chair of Logistics and Quantitative Methods ( email )

Sanderring 2
Wuerzburg, D-97070
Germany

Register to save articles to
your library

Register

Paper statistics

Downloads
18
Abstract Views
83
PlumX Metrics