Abstract
Hyperplanes withm + 1 parameters are fitted by minimizing the sum of weighted orthogonal deviations to a set ofN points. There is no inverse regression incompatibility. For unweighted orthogonall 1-fits essentially the same number of points are on either side of an optimal hyperplane. The criterion function is neither convex, nor concave, nor even differentiable. The main result is that each orthogonall p -fit interpolates at leastm + 1 points, for 0 <p ≤ 1. This enables the combinatorial strategy of systematically trying all possible hyperplanes which interpolatem + 1 data points.
This is a preview of subscription content, log in via an institution to check access.
References
R.J. Adcock, “A problem in least squares”,Analyst 5 (1878) 53.
G. Appa and C. Smith, “OnL 1 and Chebyshev estimation”,Mathematical Programming 5 (1973) 73–87.
I. Barrodale and F.D.K. Roberts, “Applications of mathematical programming tol p approximation”, in: J.B. Rosen, O.L. Mangasarian and K. Ritter, eds.,Nonlinear Programming (Academic Press, New York, 1970) pp. 447–464.
H.L. Harter, “The method of least squares and some alternatives”, Parts I–VI,International Statistical Review 42 (1974) 147–174, 235–264, 282; 43 (1975) 1–44, 125–190, 269–278; 44 (1976) 113–159.
K.A. Kermack and J.B.S. Haldane, “Organic correlation and allometry”,Biometrika 37 (1950) 30–41.
K. Pearson, “On lines and planes of closest fit to systems of points in space”,Philosophical Magazine and Journal of Science, Sixth Series 2 (1901) 559–572.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Norback, J.P., Morris, J.G. Fitting hyperplanes by minimizing orthogonal deviations. Mathematical Programming 19, 102–105 (1980). https://doi.org/10.1007/BF01581631
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01581631