Probabilistic Thinking

• Published in: Evidence-Based Decision-Making pp. 95 - 112
• Main Author: Banasiewicz, Andrew D.
• Format: Book Chapter
• Language: English
• Published: Routledge 2019
• Edition: 1
• Subjects: Average Income; Cultural DNA; Car Insurance; Causal Statistical Relationships; Multiple Subject Matter Experts; Behavioral Aggregation; Underlying Sample Size; Linear Opinion Pools; Analyses Ready Data; Probabilistic Evidence; Decision Maker’s Uncertainty; Individual Research Studies; Peer Selection Process; Support Data Curation; Evidence Pooling; Large Hadron Collider Experiments; Product Reviewers; Inter-reviewer Reliability; Resultant Knowledge Base; Preference Consistent Information; COSO’s Enterprise Risk Management; Face Validity Assessments; Computational Thinking; Scientific Theory Testing
• ISBN: 1138485292; 9781138485198; 9781138485297; 1138485195
• DOI: 10.4324/9781351050074-6

This chapter examines the interplay between the broad and general notion of probability and the idea of multi-source evidence amalgamation, evaluation, and synthesis. When looked at from a more practical or operational perspective, the goal of the ensuing analysis is to lay out a general rationale and the ‘how-to’ mechanics detailing the process that can be used to conclusively summarize the totality of dissimilar and divergent evidence. Organizational decision-making commonly entails making choices under conditions of uncertainty, in which context objective evidence offers means of reducing choice-related doubts. Expert judgment is commonly viewed as one of the most dependable sources of subjective evidence because it allows decision-makers to tap into the tacit knowledge accumulated by those with considerable experience and expertise in a domain of knowledge. The rich diversity of types and sources of organizational data is suggestive of a need for metadata, which somewhat tautologically defined, is data about data.