Estimators for Small Samples
9th general colloquium of 2006
by Professor Stephan Morgenthaler
Abstract: In problems where measurements are expensive, statisticians are often asked to analyze small sets of one, two or three data points. In this talk I will review the Pitman estimator, which is in some sense the best possible choice. In order to obtain practical estimators, however,
generalizations are needed. The Pitman estimator is best in a narrow sense, assuming a precise model. In the second part of the talk I will discuss how to construct estimates that are best in a broader sense.
For More Information: Ole Warnaar tel. 8344 5214 or Paul Pearce tel. 8344 4470