Questions & Answers

Several methods are available for finding minimum variance unbiased estimators for functions of distribution parameters. This paper concentrates on two which are rarely used but simple when applicable. The first, previously discussed by Davis (1951) and Tate (1959), yields estimators by differentiation when the range of nonzero probability for a continuous random variable depends on an unknown parameter. The second, which has wider applicability, permits estimators for some rather complicated functions to be found by using some well-known results from distribution theory. A number of examples are presented, many of which are suitable for classroom exercises.     

Questions & Answers

In the univariate case, the Poisson probability function can be derived as the limiting form of the binomial probability function as n →∞ such that np → m (fixed). The present note gives a similar derivation of the bivariate Poisson probability function as the limiting form of the bivariate binomial probability function.     

Questions & Answers: The Role of Mathematical Models in Clinical Research

Given any generalized inverse (X'X)^? appropriate to normal equations X'Xb ⁰ = X'y for the linear model y = Xb + e, a procedure is given for obtaining from it a generalized inverse appropriate to a restricted model having restrictions P'b = 0 for P'b nonestimable.     

Questions & Answeres: Reflections on Forecasting

Dedicated to the late Professor J. B. S. Haldane who brought to my attention the following very significant story from the ancient Indian epic Mahabharat (Nala—Damayanti Akhy[abar]n): The king lost his way in a jungle and was required to spend the night in a tree. The next day he told some fellow traveller that the total number of leaves on the tree were “so many”. On being challenged as to whether he counted all the leaves he replied; “No, but I counted leaves on a few branches of the tree and I know the science of die throwing”. (I can vouch for accurateness of the reproduction only in the essential respects.)     

Questions & Answers: Statistical Aspects of Chronology

For discrete statistical models it is shown that any statistic induces a partition of the set of all possible distributions defined on the sample space. This partition identifies the subsets of the parameter space for which the statistic is sufficient.     

NISO Webinar: The Future of Integrated Library Systems: Part 1: RDA & Cataloging

This column's offerings cover late spring through summer to fall of 2011: NISO Webinar: The Future of Integrated Library Systems: Part 1: RDA & Cataloging (May 11); American Library Association Annual Conference (June 23–28); Association of College and Research Libraries New England Serials and Electronic Resources Interest Group Summer Program: Current Trends in E-Journals (August 18); Kentucky Library Association/Kentucky School Media Association Joint Conference (September 28–October 1); American Society for Information Science and Technology Annual Meeting (October 9–12); Great Lakes E-Summit Conference (October 10–11); and Potomac Technical Processing Librarians Annual Meeting (October 21).