Asymptotic risk stability resulting from play against the past in a sequence of decision problems

When a given statistical decision problem occurs repeatedly, there is interest in the strategy that plays Bayes versus the empirical distribution of past parameter values. We point out some implications that some previously investigated continuity conditions have on the stability of average loss, risk, and average risk across the sequence of decision problems. This is done first for arbitrary parameter sequences and then in the context of independent and identically distributed parameters.

[1]  J. V. Ryzin,et al.  The Sequential Compound Decision Problem with $m \times n$ Finite Loss Matrix , 1966 .

[2]  H. Robbins.  An Empirical Bayes Approach to Statistics , 1956 .

[3]  Dennis Gilliland.  Approximation to Bayes Risk in Sequences of Non-finite Games , 1969 .

[4]  J. Van Ryzin,et al.  Rate of Convergence in the Compound Decision Problem for Two Completely Specified Distributions , 1965 .

[5]  D. Gilliland.  Sequential Compound Estimation , 1968 .

[6]  M. Johns.  Two-action compound decision problems , 1967 .

[7]  E. Samuel,et al.  Sequential Compound Rules for the Finite Decision Problem , 1966 .

[8]  H. Robbins.  The Empirical Bayes Approach to Statistical Decision Problems , 1964 .

[9]  E. Samuel.  Convergence of the Losses of Certain Decision Rules for the Sequential Compound Decision Problem , 1964 .

[10]  T. Hou.  Weak Approachability in a Two-Person Game , 1969 .

[11]  L. Baum,et al.  Infinitely repeated matrix games for which pure strategies suffice , 1963 .

[12]  Stanislav Jílovec,et al.  Repetitive play of a game against nature , 1967 .

[13]  E. Samuel.  Asymptotic Solutions of the Sequential Compound Decision Problem , 1963 .

[14]  E. Samuel.  Sequential Compound Estimators , 1965 .

[15]  J. M. Danskin,et al.  Fictitious play for continuous games , 1954 .

[16]  Robert Schlaifer.  Introduction to statistics for business decisions , 1963 .

[17]  V. Fabian,et al.  Experience in statistical decision problems , 1956 .

[18]  H. Robbins,et al.  Asymptotic Solutions of the Compound Decision Problem for Two Completely Specified Distributions , 1955 .

[19]  D. Blackwell.  An analog of the minimax theorem for vector payoffs. , 1956 .

[20]  J. V. Ryzin,et al.  Repetitive Play in Finite Statistical Games with Unknown Distributions , 1966 .

[21]  J. Robinson.  AN ITERATIVE METHOD OF SOLVING A GAME , 1951, Classics in Game Theory.

[22]  T. Hou.  Approachability in a Two-person Game , 1971 .

[23]  B. Shubert.  Bayesian Model of Decision-Making as a Result of Learning From Experience , 1969 .

[24]  M. Katz.  Infinitely repeatable games. , 1960 .