In this book, Professor Kreps presents a first course on the basic models of choice theory that underlie much of economic theory. This course, taught for several years at the Graduate School of Business, Stanford University, gives the student an introduction to the axiomatic method of economic analysis, without placing too heavy a demand on mathematical sophistication.
The course begins with the basics of choice and revealed preference theory and then discusses numerical representations of ordinal preference. Models with uncertainty come next: First is von Neumann–Morgenstern utility, and then choice under uncertainty with subjective uncertainty, using the formulation of Anscombe and Aumann, and then sketching the development of Savage's classic theory. Finally, the course delves into a number of special topics, including de Finetti's theorem, modeling choice on a part of a larger problem, dynamic choice, and the empirical evidence against the classic models. --back cover
An essential text, of course. One must admire the humor and casualness Kreps employs, it works very well as we need to carefully consider the normative claims in place here. I’m not sure how I feel about the weighting—if we’re to get into the weeds on mixture spaces to deploy the Mixture Space Theorem alongside vNM (a very good, very instructive tactic, to be clear. Took me a very long time to understand, but I’m glad I was exposed to it), then surely we should put some more effort into proving Savage and de Finetti (or at least some intuition for the latter). Didn’t go through the problems, so can’t speak to those, but otherwise, about as good an introduction to the subject as one can hope for (aside from when Kreps throws in a consumption savings problem in the last 20 pages—fuck off!).
I really enjoyed Krep's informal style in this book. I didn't work through this book so there is still a lot of subject matter for me to go back and visit again, but the book is certainly worth reading through in a casual way.
Great little book, if you can find it. These are lecture notes, and as such they are somewhat incomplete, and do require the reader to fill in the gaps. On the other hand, the prose is in the usual engaging an conversational style that Kreps adopts in his textbooks. The material is advanced, so the target audience of this book is really graduate school students in the social sciences (or extremely keen advanced undergraduates). It covers a lot of ground, from basic preference theory, going through expected utility, to Ansombe and Aumann and Savage.