Abstract
In this contribution, we extend the existing theory of minimum mean squared error prediction (best prediction). This extention is motivated by the desire to be able to deal with models in which the parameter vectors have real-valued and/or integer-valued entries. New classes of predictors are introduced, based on the principle of equivariance. Equivariant prediction is developed for the real-parameter case, the integer-parameter case, and for the mixed integer/real case. The best predictors within these classes are identified, and they are shown to have a better performance than best linear (unbiased) prediction. This holds true for the mean squared error performance, as well as for the error variance performance. We show that, in the context of linear model prediction, best predictors and best estimators come in pairs. We take advantage of this property by also identifying the corresponding best estimators. All of the best equivariant estimators are shown to have a better precision than the best linear unbiased estimator. Although no restrictions are placed on the probability distributions of the random vectors, the Gaussian case is derived separately. The best predictors are also compared with least-squares predictors, in particular with the integer-based least-squares predictor introduced in Teunissen (J Geodesy, in press, 2006).
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Baarda W (1968) A testing procedure for use in geodetic networks. Netherlands Geodetic Commission, Publications on Geodesy, New Series, Vol. 2, No. 5, Delft, The Netherlands
Betti B, Crespi M, Sanso F (1993) A geometric illustration of ambiguity resolution in GPS theory and a Bayesian approach. Manuscr Geod 18:317–330
Bibby JM, Toutenburg H (1977) Prediction and improved estimation in linear models. Wiley, New York
Blais JAR (1982) Synthesis of Kriging estimation methods. Manuscr Geod 7:325–352
Cressie N (1991) Statistics for spatial data. Wiley, New York
Dermanis A (1980) Adjustment of geodetic observations in the presence of signals. Bollettino di Geodesia e Scienze Affini 38:419–445
Eeg J, Krarup T (1973) Integrated geodesy. Dan. Geod. Inst., int. rep. 7, Copenhagen
Gandin LS (1963) Objective analysis of meteorological fields. Gidrometeorologicheskoe Izdatel’stvo (GIMIZ), Leningrad
Grafarend EW (1976) Geodetic applications of stochastic processes. Phys Earth Planet Interiors 12:151–179
Grafarend EW, Rapp RH (eds)(1980) Advances in geodesy. Selected papers from Rev Geophys Space Phys, Richmond, Virg., Am Geophys Union, Washington
Gundlich B, Koch KR (2002) Confidence regions for GPS baselines by Bayesian statistics. J Geod 76:55–62
Gundlich B, Teunissen PJG (2004) Multiple models: fixed, switching and interacting. In: Proceedings V Hotine-Marussi Symposium 2002, Matera, Italy, Band 127, Reihe: International Association of Geodesy Symposia, 2004
Hein GW (1986) Integrated geodesy. In: Suenkel H (ed) Mathematical and numerical techniques in physical geodesy. Lecture Notes in Earth Sciences, Vol 7. Springer, Berlin, pp 505–548
Journel AG, Huijbregts ChJ (1991) Mining geostatistics. Academic, New York
Koch KR (1980) Parameterschaetzung und Hypothesetests in linearen Modellen. Dummler, Bonn
Kolmogorov AN (1941) Interpolation and extrapolation of stationary random sequences. Izvestiia Akademii Nauk SSSR, Seriia Matematicheskiia 5:3–14
Krarup T (1969) A contribution to the mathematical foundation of physical geodesy. Publ. Danish Geod. Inst. 44, Copenhagen
Krarup T (1980) Integrated geodesy. Bollettino di Geodesia e Scienze Affini 38:480–496
Krige D (1951) A statistical approach to some basic mine valuation problems on the Witwatersrand. J Chem Metall Min Soc S Afr 52:119–139
Matheron G (1970) The theory of regionalized variables and its applications. Fascicule 5, Les Cahiers du Centre de Morphologie Mathematique, Ecole des Mines de Paris, Fontainebleau, 211p
Moritz H (1973) Least-squares collocation. Deutsche Geodaetische Kommission, Reihe A, No. 59, Muenchen
Moritz H (1980) Advanced physical geodesy. Wichmann, Karlsruhe
Moritz H, Suenkel H (Eds) (1978) Approximation methods in geodesy. Sammlung Neue Folge, Band 10, Karlsruhe
Rao CR, Toutenburg H (1999) Linear models: least squares and alternatives. Springer Series in Statistics, Berlin
Reguzzoni M, Sanso F, Venuti G (2005) The theory of general kriging, with applications to the determination of a local geoid. Geophys J Int 162:303–314
Rummel R (1976) A model comparison in least-squares collocation. Bull Geod 50:181–192
Sanso F (1980) The minimum mean square estimation principle in physical geodesy. Bollettino di Geodesia e Scienze Affini 39(2):111–129
Sanso F (1986) Statistical methods in physical geodesy. In: Suenkel H (ed) Mathematical and numerical techniques in physical geodesy, Lecture Notes in Earth Sciences, Vol. 7. Springer, Berlin, pp 49–156
Stark H (ed) (1987) Image recovery: theory and application. Academic, New York
Teunissen PJG (1995) The least-squares ambiguity decorrelation adjustment: a method for fast GPS integer ambiguity estimation. J Geod 70:65–82
Teunissen PJG (1999) An optimality property of the integer least-squares estimator. J Geod 73:587–593
Teunissen PJG (2001) Statistical GNSS carrier phase ambiguity resolution: a review. In: Proceedings IEEE Symposium Statistical Signal Processing, pp 4–12
Teunissen PJG (2003) Theory of integer equivariant estimation with application to GNSS. J Geod 77:402–410
Teunissen PJG (2006) Least-squares prediction in linear models with integer unknowns. J Geodesy (in press). DOI 10.1007/s00190-007-0138-0
Teunissen PJG, Simons DG, Tiberius CCJM (2005) Probability and Observation Theory. Lectures Notes Delft University of Technology, Delft, The Netherlands
Tscherning CC (1978) Collocation and least-squares methods as a tool for handling gravity field dependent data obtained through space research techniques. Bull Geod 52:199–212
Wackernagel H (1995) Multivariate geostatistics. Springer, Berlin
Wiener N (1949) Extrapolation, interpolation, and smoothing of stationary time series. MIT, Cambridge
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Open Access This is an open access article distributed under the terms of the Creative Commons Attribution Noncommercial License ( https://creativecommons.org/licenses/by-nc/2.0 ), which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
About this article
Cite this article
Teunissen, P.J.G. Best prediction in linear models with mixed integer/real unknowns: theory and application. J Geod 81, 759–780 (2007). https://doi.org/10.1007/s00190-007-0140-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00190-007-0140-6