To the data analyst, outliers can present both a problem and an opportunity. Stray or outlying observations can severly distort estimates of a distribution's central tendency (like the mean) and estimates of one variable's relationship to another (like the regression coefficient). These problems are frequent and serious, and as a result, increasing numbers of statisticians are developing new estimating procedures that are robust in the face of outliers. But outliers may also present an opportunity. An unusual observation may indicate the existence of a process not operating in the rest of the distribution. In education, for example, an outlier may turn out to be an unusually effective school, perhaps one worthy of emulation throughout the educational system. Finding the best by locating outliers may be particularly important in the evaluation of public policies. Can one find exceptionally good police forces and study the causes for their success? What about outstanding rural development projects, exceptional hospitals, and unusally effective manpower training programs? Indeed, one may suggest a worthwhile general rule for policy evaluations: For exceptions to the general rules, include a search for unusual performers. (Author)