6533b838fe1ef96bd12a4f53
RESEARCH PRODUCT
Conditional Versus Joint Probability Assessments
Herbert MoskowitzJyrki WalleniusJyrki Walleniussubject
021103 operations researchChain rule (probability)Process (engineering)Posterior probability0211 other engineering and technologies02 engineering and technologyComputer Science ApplicationsJoint probability distributionConsistency (statistics)Signal ProcessingStatistics0202 electrical engineering electronic engineering information engineeringEconometricsProbability calculus020201 artificial intelligence & image processingInformation SystemsMathematicsdescription
AbstractThe assessment of conditional and / or joint probabilities of events that constitute scenarios is necessary for sound planning, forecasting, and decision making. The assessment process is complex and subtle, and various difficulties are encountered in the elicitation of such probabilities such as, implicit violations ofthe probability calculus and some meaningfjilness conditions. The necessary and sufficient as well as meaningfulness conditions that the elicited information on conditional and joint probabilities must satisfy are evaluated against actual assessments empirically. A high frequency of violation of these conditions was observed in assessing both conditional and joint probabilities. The consistency of the assessments is affected by factors such as the causal / diagnostic and positive / negative relationship of the events. Use of a joint probability table as a judgmental aid can significantly reduce the number of inconsistent conditional as well as joint probability assessments. The impl...
| year | journal | country | edition | language |
|---|---|---|---|---|
| 1984-05-01 | INFOR: Information Systems and Operational Research |