Decomposition and the Control of Errors in Decision Analytic Models (Classic Reprint)

In Decomposition and the Control of Errors in Decision Analytic Models, this book explains how breaking big decisions into smaller parts can improve reliability. It argues that linear decompositions offer a practical way to reduce random errors and make complex modeling easier to understand and use.

The work frames decision analysis as an engineering approach that blends normative theory with descriptive findings. It shows how decomposition helps decision makers focus on individual components, while noting the limits and tradeoffs of different methods. The discussion covers when decomposition works best, how to manage potential biases, and what to consider when choosing detail levels in a model.

• How linear decompositions can reduce random error and improve consistency in judgments


• Ways to reduce component errors, including model-based estimation and nesting decomposition


• Impacts of weighting schemes and how to handle dependent errors


• Guidance on selecting the right level of detail for a decision model

Ideal for readers of decision analysis, risk assessment, and research in decision making, this edition offers practical insights for researchers and practitioners alike.