Comment on “Newsvendor Demand Chasing Revisited”

Kirshner, Samuel N.; Moritz, Brent

doi:10.1287/mnsc.2019.3489

Cited by 6 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kirshner and Moritz (2020) showed that there were two limitations in the simulation approach of Lau and Bearden (2013). First, Lau and Bearden's (2013) numerical study did not address gambler's fallacy behavior, which reflects a subject's tendency to decrease ( increase ) their order if demand in the prior period was high (low) Gambler's fallacy behavior is consistent with negative correlation between order and prior demand and has been observed in prior experiments (e.g., Bolton & Katok, 2008) Lau and Bearden (2013) excluded the potential for gambler's fallacy behavior by reporting only one‐sided t ‐tests (

α = 0.025

t_{c r i t} \geq 2.045

) when the simulated correlation could be positive or negative, which understates the false‐positive rate.…”

Section: Prior Researchmentioning

confidence: 99%

“…Several papers have noted that Equation () is one plausible behavioral model that provides a foundation for other models. Kirshner and Moritz (2020) discussed a more complex partial adjustment model, an extended version of which was used by Lurie and Swaminathan (2009):

q_{t} = β_{0} + β_{1} (d_{t - 1} - q_{t - 1}) + β_{2} q_{t - 1} + ε_{t} .

…”

Section: Prior Researchmentioning

confidence: 99%

“…Although Equation () was not evaluated by Lau and Bearden (2013), they considered it the same regression approach. Kirshner and Moritz (2020) demonstrated that the slight difference between Equation () and Equation () eliminated the false positives reported by Lau and Bearden (2013) under the condition when orders were simulated via quantal choice, although Equation () outperformed Equation () under simulated demand chasing.…”

Section: Prior Researchmentioning

confidence: 99%

“…Hyndman and Embrey (2018) estimated the parameters

δ_{0}

δ_{1}

, and

δ_{2}

using OLS, fixed effects, random effects, three different dynamic panel data models, and subject specific regression (as in Lau & Bearden, 2013 and Kirshner & Moritz, 2020) for data where orders are generated around a subject specific constant with noise. With a panel structure, they found that the OLS is biased, whereas the other methods are effective.…”

Section: Prior Researchmentioning

confidence: 99%

“…When demand is uniformly distributed, Proposition 1 of Su (2008) shows that the quantal choice model leads to orders that follow a truncated normal distribution where the variance of the order

s^{2}

is proportional to

γ

. Following Lau and Bearden (2013) and Kirshner and Moritz (2020), we consider a quantal choice model where the orders are drawn from a truncated normal distribution with a mean of 50 and extend the set of considered variances to

s \in {5, 10, 15, 20}

. Observe that the orders approximate a white noise process.…”

Section: Simulation Studiesmentioning

confidence: 99%

See 4 more Smart Citations

Measuring demand chasing behavior

Kirshner

Moritz

2021

Decision Sciences

Self Cite

View full text Add to dashboard Cite

Chasing behavior is an example of the anchoring and adjustment heuristic that occurs in many business contexts. In inventory management settings, decision makers often engage in demand chasing by adjusting order quantities toward recent demand observations. This can result in lower profit for the firm and increased variability across the supply chain. Prior research suggests that demand chasing can be measured by regression or correlation. Using two empirical datasets, we show that the observed costs associated with chasing are better captured using regression. We complement our empirical findings through comprehensive simulations across a range of order generating functions, supporting the robustness of regression models. Finally, we discuss behavioral differences between approaches and explain why certain models are better equipped for measuring demand chasing.

show abstract

α = 0.025

t_{c r i t} \geq 2.045

) when the simulated correlation could be positive or negative, which understates the false‐positive rate.…”

Section: Prior Researchmentioning

confidence: 99%

q_{t} = β_{0} + β_{1} (d_{t - 1} - q_{t - 1}) + β_{2} q_{t - 1} + ε_{t} .

…”

Section: Prior Researchmentioning

confidence: 99%

Section: Prior Researchmentioning

confidence: 99%

“…Hyndman and Embrey (2018) estimated the parameters

δ_{0}

δ_{1}

, and

δ_{2}

Section: Prior Researchmentioning

confidence: 99%

“…When demand is uniformly distributed, Proposition 1 of Su (2008) shows that the quantal choice model leads to orders that follow a truncated normal distribution where the variance of the order

s^{2}

is proportional to

γ

s \in {5, 10, 15, 20}

. Observe that the orders approximate a white noise process.…”

Section: Simulation Studiesmentioning

confidence: 99%

See 3 more Smart Citations

Measuring demand chasing behavior

Kirshner

Moritz

2021

Decision Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

Reference‐dependent preferences in flat penalty service‐level contracts

Duhaylongsod

Papier

Öncüler

2023

J of Ops Management

View full text Add to dashboard Cite

This paper investigates a supply chain governed by a flat penalty service‐level contract in which missing the target fill rate can lead to costly operational disruption. We focus on near‐miss bias: (1) the preference for near‐miss events, that is, risky production quantities that reach the target but narrowly avoid disruption; and (2) riskier decision‐making due to such preferences. We propose a reference‐dependent behavioral model that explains the near‐miss bias. The findings of a laboratory experiment show that production quantities are evaluated based on realized profits and are below the optimal model prediction. Contracts associated with lower perceived severity, that is, the ratio of flat penalty to wholesale price, result in lower production quantities than those with higher perceived severity, even though the standard model does not predict any effect. A structural estimation analysis indicates that the behavioral model performs better than the standard model in terms of predictive accuracy and goodness of fit. Our analysis provides insights for managers who design supply chain contracts in settings with considerable risk of disruption due to a shortage of critical parts.

show abstract

Predicting mean and variance in inventory order decisions

Chen,

Davis,

Kim

2024

Decision Sciences

View full text Add to dashboard Cite

We develop a simple forecast‐anchoring model to explain and predict the mean and variance of observed inventory order decisions in a newsvendor problem. The model assumes that people employ a two‐step decision heuristic. In the first step, a behavioral bias may gravitate the decision maker's point forecast toward a random forecast versus a constant unbiased forecast. In the second step, a behavioral bias of the same magnitude may cause the decision maker to treat the point forecast as if it is the mean of potential demand, and then make an upward or downward adjustment depending on the underage and overage costs. We evaluate the performance of this descriptive forecast‐anchoring model across five experimental newsvendor data sets. First, we fit the model to a setting with uniform demand. We then use the corresponding estimates to generate predictions in a secondary data set with uniform demand, as an out‐of‐sample test. We proceed to fit the model to three additional newsvendor data sets, two with normal demand and one with asymmetric two‐point demand. In all cases, the model predicts the mean and variance of inventory order decisions well. We further investigate the profit implications under the forecast‐anchoring model and find that the predictions match well with the experimental data. Through improved predictions, the model can help upstream supply chain parties anticipate inventory order decisions from buyers and improve profitability.

show abstract

Comment on “Newsvendor Demand Chasing Revisited”

Cited by 6 publications

References 10 publications

Measuring demand chasing behavior

Measuring demand chasing behavior

Reference‐dependent preferences in flat penalty service‐level contracts

Predicting mean and variance in inventory order decisions

Contact Info

Product

Resources

About