The method of least squares enables the determination of an estimate of the slope and intercept of a straight line relationship between two quantities or variables X and Y. Although a theoretical relationship may exist between X and Y of the form Y = mX + c, in practice experimental or measurement errors will occur, and the observed or measured values x and y may not lie exactly on a straight line. In this paper, the author discusses ordinary least squares (OLS) and total least squares (TLS), as well as the use of orthogonal distances in generating the TLS estimate. He believes that the applicability OLS and TLS formulas should be stressed to students, particularly the possibility of errors in both variables. (Contains 4 figures and 2 tables.)