When sitting in statistics classes or when trying to read and understand
statistical material, too many otherwise intelligent and capable students and
researchers feel dumb. This book is intended as an antidote. It is designed to
make you feel smart and competent. Its approach is conservative in that it
attempts to identify and present the essentials of data analysis as developed by
statisticians over the last two or three centuries.
In a classification problem, you typically have historical data (labeled examples)
and unlabeled examples. Each labeled example consists of multiple predictor
attributes and one target attribute (dependent variable). The value of the target
attribute is a class label. The unlabeled examples consist of the predictor attributes
only. The goal of classification is to construct a model using the historical data that
accurately predicts the label (class) of the unlabeled examples.
The number one predictor of successful salespeople is their ability to
connect with their customers. In the years leading up to the present,
the best sales executives have accomplished this by having multiple,
face-to-face meetings. However, the demands on our clients’ time,
coupled with the increasing expense and frustration of travel, have
minimized our ability to actually meet with clients.
After studying this chapter you will be able to understand: How to classify and select multivariate techniques, that multiple regression predicts a metric dependent variable from a set of metric independent variables, that discriminant analysis classifies people or objects into categorical groups using several metric predictors.