ABSTRACT

In this chapter we face the major challenge of modern statistics, devising and analyzing

methods of inference for high dimensional complex data. The issues we discuss in this

chapter are:

1. Prediction with high dimensional covariates

Under this heading we will consider classification, regression and prediction problems

now associated with machine learning, and statistical learning. The methods we shall

briefly discuss include ones easily related to statistical methods such as the univariate curve

estimation in Chapter 11 and the logistic regression in Sections 6.4.3 and 6.5; and ones

more closely related to machine learning such as support vector machines and boosting.