Other editions - View all
actually additive alternatives analysis apply approach approximation argue argument assume Barnard Bayesian Bayesian analysis Berger Birnbaum called censoring choice classical clear concerning conclusion conditional consider consideration contains continuous course criticism decision defined definition density depend discussion error essentially estimator Evaluation evidence example exists experiment experimenter finitely formal Foundations frequentist given gives hence Hill ignored important independent indicate inference interest interpretation involve issue known least likelihood function likelihood principle mean measures mechanism methods noninformative Note nuisance objective observed obtained parameter particular performance possible posterior practical present prior distribution probability problem procedure Professor question random reasonable reject relevant respect result sample seems sense significance simple situation space Statist stopping rule sufficient Suppose testing theory theta uniform University unknown usually variable violation
Page 174 - Objective evidence and certitude are doubtless very fine ideals to play with, but where on this moonlit and dream-visited planet are they found? I am, therefore, myself a complete empiricist so far as my theory of human knowledge goes. I live, to be sure, by the practical faith that we must go on experiencing and thinking over our experience, for only thus can our opinions grow more true...
Page 174 - I am, therefore, myself a complete empiricist so far as my theory of human knowledge goes. I live, to be sure, by the practical faith that we must go on experiencing and thinking over our experience, for only thus can our opinions grow more true ; but to hold any one of them — I absolutely do not care which — as if it never could be re-interpretable or corrigible, I believe to be a tremendously mistaken attitude, and I think that the whole history of philosophy will bear me out.
Page 79 - ... have precisely determined alternatives, with which you want to compare a given hypothesis, and you use another method when you do not have these alternatives. SAVAGE: May I digress to say publicly that I learned the stoppingrule principle from Professor Barnard, in conversation in the summer of 1952. Frankly, I then thought it a scandal that anyone in the profession could advance an idea so patently wrong, even as today I can scarcely believe that some people resist an idea so patently right.
Page 74 - This irrelevance of stopping rules to statistical inference restores a simplicity and freedom to experimental design that had been lost by classical emphasis on significance levels (in the sense of Neyman and Pearson) and on other concepts that are affected by stopping rules. Many experimenters would like to feel free to collect data until they have either conclusively proved their point, conclusively disproved it, or run out of time, money, or patience.
Page 63 - In the past, the need for probabilities expressing prior belief has often been thought of, not as a necessity for all scientific inference, but rather as a feature peculiar to Bayesian inference. This seems to come from the curious idea that an outright assumption does not count as a prior belief... I believe that it is impossible logically to distinguish between model assumptions and the prior distribution of the parameters.
Page 102 - What the use of P implies, therefore, is that a hypothesis that may be true may be rejected because it has not predicted observable results that have not occurred.
Page 149 - Bayesian and classical influence in the analysis of variance and in the testing of models. In DL Meyer & RO Collier, Jr.
Page 8 - A cv = s/x, (4.1) where x and s are the sample mean and standard deviation, respectively.
Page 156 - Berger, JO and Delampady, M. (1987). Testing Precise Hypotheses. With Discussion. Statistical Science 2, 317-352. Berger, JO and Mortera, J.
Page 62 - ... Would you offer 19 to 1 odds that the standard deviation of the height of Meccans is less than 1-13 mm? That is the 95 per cent upper confidence limit computed from chi-squared with one degree of freedom. No, I think you would not have even enough confidence in that limit to offer odds of 1 to 1 . The only use I know for a confidence interval is to have confidence in it.