• Corpus ID: 833805

Comparison of Experiments

  title={Comparison of Experiments},
  author={David Blackwell},
1. Summary Bohnenblust, Shapley, and Sherman [2] have introduced a method of comparing two sampling procedures or experiments; essentially their concept is that one experiment a is more informative than a second experiment ,, a v ,S, if, for every possible risk function, any risk attainable with , is also attainable with a. If a is a sufficient statistic for a procedure equivalent to ,S, a >,, it is shown that a v j3. In the case of dichotomies, the converse is proved. Whether > and v are… 

Comparing Location Experiments

In Sections 1–3, the classical theory of the comparison of two experiments is reviewed with particular reference to the comparison of two location experiments. It is shown that the requirement of


  • Mathematics
  • 1989
Introduction. The theory of comparison of experiments deals with the following problem. Suppose two kinds of observations are available to a statistician. The observations are of two random variables

On Neyman-Pearson Theory: Information Content of an Experiment and a Fancy Paradox

Two topics, connected with Neyman-Pearson theory of testing hypotheses, are treated in this article. The first topic is related to the information content of an experiment; after a short outline of

Criterios para la comparacion de experimentos

ResumenIn the present paper we consider those situations in which the statistician expects getting information about a given parametric space by means of observing several random variables, called

Comparison of sequential experiments

Introduction. The theory of comparison of experiments deals with the following problem. Suppose two kinds of observations are available to a statistician. The observations are of two random variables

Information Structures on a General State Space: An Equivalence Theorem and an Application

Blackwell's (1949) theorem on the comparison of information structures has been influential in both theoretical and applied work in economics, statistics and game theory, but severely hampered by its

When is one experiment ‘always better than’ another?

Summary.  Considering the choice between two experiments E and F, an experimenter may choose one or the other depending on the optimality criteria. However, sometimes by using the observations from

Cardinal Representations of Information

In the spirit of von Neumann and Morgenstern (1947), this paper provides an axiomatic representation of information. Under the von Neumann-Morgenstern axioms, along with an additional continuity,

Comparison of experiments when the parameter space is finite

The convex function criterion for "being more informative" for k-decision problems is-in Section 2-generalized to a convex function criterion for edeficiency for k-decision problems. The particular

A possible foundation for Blackwell’s Equivalence

The Sufficiency Principle states that it is equal for the Statistician to observe the full data or a sufficient statistic. Nevertheless, it can only be used as a criterion for the comparison of



Regularity properties of certain families of chance variables

with probability 1. The subscript n here is any positive integer. It will always be supposed that the given chance variables have expectations, so that the conditional expectations involved in the

Application of the Radon-Nikodym Theorem to the Theory of Sufficient Statistics

The body of this paper is written in terms of very general and abstract ideas which have been popular in pure mathematical work on the theory of probability for the last two or three decades. It

Some Methods applicable to Identities and Inequalities of Symmetric Algebraic Functions of n Letters

The methods explained here are applicable to a large number of problems relating to the symmetric algebraic functions of n letters, and the special results here deduced from them are merely specimens

Some Problems in Minimax Point Estimation

In the present paper the problem of point estimation is considered in terms of risk functions, without the customary restriction to unbiased estimates. It is shown that, whenever the loss is a convex

Left centralizers and isomorphisms of group algebras

The principal result (Theorem 1) of Part I states that, conversely, every left centralizer is a convolution with a regular measure. Important auxiliary theorems (3 and 4) furnish a characterization