Ryall and Bramson's Inference and Intervention is the first textbook on causal modeling with Bayesian networks for business applications. In a world of resource scarcity, a decision about which business elements to control or change - as the authors put it, a managerial intervention - must precede any decision on how to control or change them, and understanding causality is crucial to making effective interventions.
The authors cover the full spectrum of causal modeling techniques useful for the managerial role, whether for intervention, situational assessment, strategic decision-making, or forecasting. From the basic concepts and nomenclature of causal modeling to decision tree analysis, qualitative methods, and quantitative modeling tools, this book offers a toolbox for MBA students and business professionals to make successful decisions in a managerial setting.
Publisher: Taylor & Francis Ltd
Number of pages: 266
Weight: 658 g
Dimensions: 254 x 178 mm
"One of the most difficult problems any real world decision maker faces is how to properly incorporate prior information into current decisions. Modes of analysis used by management consultants such as issue trees direct our thinking away from this key question of causality. This stunning book by Ryall and Bramson introduces causal models as a method of focusing our attention on what is important: Why are these things happening, and (therefore) what can we do about it? Both modeling and strategy are given full attention. Although this book is designed for managers and is full of practical managerial examples, it is essential reading for anyone who has to make significant decisions."
- David K. Levine, Washington University in St. Louis
"Ryall and Bramson have written a remarkable book that combines a clear, comprehensive introduction into qualitative and quantitative causal models with case studies and examples that show managers how to apply causal models to see the world more clearly and make better decisions. After reading this book, you'll quit yourã spreadsheet and start drawing causal networks instead."
- Scott E. Page, University of Michigan and Santa Fe Institute ã
You may also be interested in...
Please sign in to write a review