Also recommend Hubbard's How to Measure Anything. Background in social science & stats, so was familiar with the decision making logic before reading, but think the book is more straight forward than any other reference. (Similar in spirit is Tetlock's Superforecasters, but I think Hubbard will be easier for most people to relate to.)

My other mentions would be Algorithms to Live By (Christian and Griffiths), and Tufte's Visual Display of Quantitative Information (with a follow up of Doumont's Trees, Maps, and Theorems. Tufte I really enjoyed.

Thank you for the Deming reference -- will need to put that and Performance modelling on the list!