This is a superficial review of basic problems in linear regression analysis. The discussion is numerically oriented; it covers estimation of regression coefficients, tests of various hypotheses about them, and selection of the best subset of explanatory variables. For a comprehensive study of the selection problem and other closely related topics,
see the recent survey article by R. R. Hocking [Biometrics 32 (1976), no. 1, 1–49; MR0398008]. (MR0448720)
