Semi-Supervised Linear Regression

Abstract

We study a regression problem where for some part of the data we observe both the <i>label</i> variable (<i>Y</i>) and the <i>predictors</i> (X), while for other part of the data only the predictors are given. Such a problem arises, for example, when observations of the label variable are costly and may require a skilled human agent. When the conditional expectation E[Y|X] is not exactly linear, one can consider the best linear approximation to the conditional expectation, which can be estimated consistently by the least-square estimates (LSE). The latter depends only on the labeled data. We suggest improved alternative estimates to the LSE that use also the unlabeled data. Our estimation method can be easily implemented and has simply described asymptotic properties. The new estimates asymptotically dominate the usual standard procedures under certain non-linearity condition of E[Y|X]; otherwise, they are asymptotically equivalent. The performance of the new estimator for small sample size is investigated in an extensive simulation study. A real data example of inferring homeless population is used to illustrate the new methodology.