Subjective Probability Elicitation Techniques: A Performance Comparison

Chesley, G. R.

doi:10.2307/2490564

Cited by 24 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several methods for indirect elicitation of probabilities have been developed. Some well know methods are: the odds method; the bid method; the lottery method; the probability-wheel method; among others [17,18], these methods allow the extraction of probabilities without have to explicitly mention probabilities, so to speak.…”

Section: Probability Elicitation Methodsmentioning

confidence: 99%

Issues in the Probability Elicitation Process of Expert-Based Bayesian Networks

Nunes¹,

Barbosa²,

Silva³

et al. 2018

Enhanced Expert Systems [Working Title]

View full text Add to dashboard Cite

A major challenge in constructing a Bayesian network (BN) is defining the node probability tables (NPT), which can be learned from data or elicited from domain experts. In practice, it is common not to have enough data for learning, and elicitation from experts is the only option. However, the complexity of defining NPT grows exponentially, making their elicitation process costly and error-prone. In this research, we conducted an exploratory study through a literature review that identified the main issues related to the task of probability elicitation and solutions to construct large-scale NPT while reducing the exposure to these issues. In this chapter, we present in detail three semiautomatic methods that reduce the burden for experts. We discuss the benefits and drawbacks of these methods, and present directions on how to improve them.

show abstract

Section: Probability Elicitation Methodsmentioning

confidence: 99%

Issues in the Probability Elicitation Process of Expert-Based Bayesian Networks

Nunes¹,

Barbosa²,

Silva³

et al. 2018

Enhanced Expert Systems [Working Title]

View full text Add to dashboard Cite

show abstract

“…There are several techniques that suggest ways for eliciting subjective probabilities from expert knowledge, which can be used in this context. The studies of Chesley (1978) and Ludke, Stauss, and Gustafson (1977) provide a comparison between some of the methods. Moreover, some factors that should be taken into account when following this approach, such as bias, are analyzed in the following studies (Bunn, 1975;Bunn 1979;Spetzler & Stael Von Holstein, 1975;Winkler, 1967;Wright & Ayton, 1987).…”

Section: Populating the Model Parametersmentioning

confidence: 99%

A Supply Chain Tracking Model Using Auto-ID Observations

Kelepouris

McFarlane

Giannikas

2012

International Journal of Information Systems and Supply Chain Management

View full text Add to dashboard Cite

Order location information is undoubtedly one of the most critical pieces of supply chain information. Yet supply chain visibility generally remains a challenge as observations of order progress are often irregular and collected manually. The emergence of Automated Identification (Auto-ID) technologies like Radio Frequency Identification (RFID) is improving the effectiveness of supply chain tracking systems. The authors propose a model that describes how Auto-ID observations across a supply chain and historical observation data can be combined to produce an ongoing order location estimation over time. The model is based on probabilistic reasoning principles and the resulting location estimation can be used to support operational decisions as well as to assess the quality and value of tracking information. The authors provide explicit instructions as to how to use the proposed model and using an illustrative example, they demonstrate how the model can produce ongoing location estimates based on RFID read events.

show abstract

“…Indirect methods use responses to a question or choices based on a task designed to infer a respondents' degree of uncertainty. (Winkler (1967); Chesley (1978)), a common critique is that the interplay of an individual's risk attitude with the perceived uncertainty may influence the response and choices made by the respondent in the assessment of subjective probability (Chesley (1978)…”

Section: Introductionmentioning

confidence: 99%

“…While some researchers believe the SPIES method performs better than fractile approaches, (Winkler, 1967;Ludke et al, 1977;Chesley, 1978), there is no consensus. Further, evidence is lacking as to which method is cognitively simpler for respondents to use: the fractile method requires only equally likely responses (Chesley, 1978) but may be more difficult than the SPIES method because one-half of the distribution is disregarded (Huber, 1974). Also, it may be difficult for respondents to assess small probabilities using the fractile method because it produces relatively tight subjective distributions, particularly in the tails.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Subjective beliefs and decision making under uncertainty in the field

Agarwal¹

View full text Add to dashboard Cite

Subjective Probability Elicitation Techniques: A Performance Comparison

Cited by 24 publications

References 8 publications

Issues in the Probability Elicitation Process of Expert-Based Bayesian Networks

Issues in the Probability Elicitation Process of Expert-Based Bayesian Networks

A Supply Chain Tracking Model Using Auto-ID Observations

Subjective beliefs and decision making under uncertainty in the field

Contact Info

Product

Resources

About