ABSTRACT
This chapter discusses two sets of data. The first shows the lowest temperatures recorded for various cities in the United States. The second addresses the number of times 15 congresspeople from New Jersey voted differently in the House of Representatives on 19 environmental bills. The chapter describes the application of &-means clustering to the temperature data on US cities, and then the application of a number of hierarchical clustering procedures to the voting in Congress data. Cluster analysis is a generic term for a large number of relatively disparate techniques that seek to determine whether or not a data set contains distinct groups or clusters of observations and, if so, to find these groups.
