Linear least squares
Least squares historically grew out of astronomy problems during the turn of the seventeenth century (Nievergelt 2000), in particular, finding trajectories of planetary motions in order to solve ocean’s navigation problems. The idea of LS was developed by Gauss, Legendre, Laplace, and many other mathematicians and scientists (Farebrother 1999). However, the first publication on LS appeared in 1805 by Legendre; he proposed the idea of minimizing the sum of squares of the errors to obtain the adjusted values of observed quantities (Plackett 1972).
“Least squares” is a mathematical procedure to find the best approximate curve or surface to a given set of data points, out of different model functions that approximate the data.
Linear Least Squares
- Anderson DR, Sweeney DJ, Williams TA (1994) Introduction to statistics: concepts and applications. West GroupGoogle Scholar
- Vos D (2008) Risk analysis: a quantitative guide, 3rd edn. WileyGoogle Scholar
- Wackerly DD, Mendenhall W III, Scheaffer RL (2008) Mathematical statistics with applications, 7th edn. Cengage LearningGoogle Scholar