A Defense of the Bayesian Choice
This book has exposed the main aspects of Bayesian inference in Statistics from a decision-theoretic point of view. The coverage is obviously anything but exhaustive: on one hand, the topics we consider are often treated in more detail in the references mentioned at various points. On the other hand, Bayesian analysis can be applied to many fields, among which are Econometrics (see Zellner (1971, 1984), Box and Tiao (1973), Maddala (1977), or Chow (1983)), Time Series (see West and Harrison, 1989), applied Statistics, but also in theoretical Statistics like sequential analysis (see Pilz, 1991). Moreover, it is not surprising to find Bayesian perspectives in fields where Statistics and prior information play a role: finance and insurance, expert systems (Spiegelhalter and Cowell, 1992; Gilks et al., 1993), pattern recognition (Ripley, 1986), image processing (Geman and Geman, 1984, Besag, 1986, Geman, 1988), neural networks (Ripley, 1992), numerical analysis (Diaconis, 1988, O’Hagan, 1992), chaos theory (Berliner, 1991, 1992), etc.
KeywordsLoss Function Prior Distribution Bayesian Approach Bayesian Analysis Maximum Likelihood Estimator
Unable to display preview. Download preview PDF.