2012
DOI: 10.1214/12-ba714
|View full text |Cite
|
Sign up to set email alerts
|

Log-Linear Pool to Combine Prior Distributions: A Suggestion for a Calibration-Based Approach

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
18
0

Year Published

2014
2014
2024
2024

Publication Types

Select...
6
2
2

Relationship

0
10

Authors

Journals

citations
Cited by 26 publications
(18 citation statements)
references
References 33 publications
0
18
0
Order By: Relevance
“…Linear and logarithmic opinion pools are two well-known models which can be used to form weighted votes [36], [37]. All previously reported locally weighted voting approaches use the linear opinion pool to integrate reliability weights in the fusion process.…”
Section: Introductionmentioning
confidence: 99%
“…Linear and logarithmic opinion pools are two well-known models which can be used to form weighted votes [36], [37]. All previously reported locally weighted voting approaches use the linear opinion pool to integrate reliability weights in the fusion process.…”
Section: Introductionmentioning
confidence: 99%
“…In [39] the authors show that learning in social networks with complex neighborhood structures can be achieved if agents choose a neighbor randomly at every round and restrict their belief update to the selected neighbor each time (essentially replicating the case of a directed circle where every neighborhood is a singlton). Geometric averaging and logarithmic opinion pools have a long history in Bayesian analysis and behavioral decision models [40], [41] and they can be also justified under specific behavioral assumptions [42]. The are also quite popular as a non-Bayesian update rule in distributed detection and estimation litrature [43], [44], [10], [14], [45].…”
Section: Discussionmentioning
confidence: 99%
“…Alternatively, they could represent an estimate of expected accuracy, determined using seed questions (discussed in Conclusion), prior assessments of the expert's background 82,110,111 or agreement of the expert's elicited data with subsequently observed data on the quantity of interest, 111 although observed data would not generally be available in a health-care context. More technically advanced methods that use only the elicited data to form weights are presented by Ranjan and Gneiting, 112 Rufo et al 113 and Hora and Kardeş. 114 Essentially, these adjust the simple linear or log-pools to give a better expected balance of overall bias and over/underconfidence.…”
Section: Mathematical Aggregationmentioning
confidence: 99%