Abstract
Msplit(q) estimation is a development of M-estimation which is based on the assumption that a functional model of observations can be split into q competitive ones. The main idea behind such an assumption is that the observation set might be a mixture of realizations of different random variables which differ from each other in location parameters that are estimated. The paper is focused on the robustness of Msplit(q) estimates against outlying observations. The paper presents derivatives of the general expressions of the respective influence functions and weight functions which are the main basis for theoretical analysis. To recognize the properties of Msplit(q) estimates in a better way, we propose considering robustness from two points of view, namely local and global ones. Such an approach is a new one, but it reflects the nature of the estimation method in question very well. Thus, we consider the local breakdown point (LBdP) and the global one (GBdP) that are both based on the maximum sensitivities of the estimates. LBdP describes the mutual relationship between the “neighboring” Msplit(q) estimates, whereas GBdP concerns the whole set of the estimates and describes the robustness of the method itself (in more traditional sense). The paper also presents GBdP with an extension, which shows how an outlier might influence Msplit(q) estimates. The general theory proposed in the paper is applied to investigate the squared Msplit(q) estimation, the variant which is used in some practical problems in geodesy, surveying, remote sensing or geostatistics, and which can also be applied in other geosciences.
Similar content being viewed by others
References
Amiri-Simkooei A.R., Alaei-Tabatabaei S.M., Zangeneh-Nejad F. and Voosoghi B., 2017. Stability analysis of deformation-monitoring network points using simultaneous observation adjustment of two epochs. J. Surv. Eng., 143, 1–12 DOI: https://doi.org/10.1061/(ASCE)SU.1943-5428.0000195.
Błaszczak-Bąk W., Janowski A., Kamiński W. and Rapiński J., 2015. Application of the Msplit method for filtering airborne laser scanning data-sets to estimate digital terrain models. Int. J. Remote Sens., 36, 2421–2437.
Campbell N.A., 1984. Mixture models and atypical values. Math. Geol., 16, 465–477.
Caspary W. and Haen W., 1990. Simultaneous estimation of location and scale parameters in the context of robust M-estimation. Manuscr. Geod., 15, 273–282.
Cellmer S., 2014. Least fourth powers: optimisation method favouring outliers. Surv. Rev., 47, 411–117, DOI: https://doi.org/10.1179/1752270614Y.0000000142.
Chang X.W. and Guo Y., 2005. Huber’s M-estimation in relative GPS positioning: computational aspects. J. Geodesy, 79, 351–362.
Duchnowski R., 2011. Robustness of strategy for testing leveling mark stability based on rank test. Surv. Rev., 43, 687–699.
Duchnowski R., 2013. Hodges-Lehmann estimates in deformation analyses. J. Geodesy, 87, 873–884.
Duchnowski R. and Wiśniewski Z., 2011. Estimation of the shift between parameters of functional models of geodetic observations by applying Msplit estimation. J. Surv. Eng., 138, 1–8.
Duchnowski R. and Wiśniewski Z., 2014. Comparison of two unconventional methods of estimation applied to determine network point displacement. Surv. Rev., 46, 401–405.
Duchnowski R. and Wiśniewski Z., 2017a. Accuracy of the Hodges-Lehmann estimates computed by applying Monte Carlo simulations. Acta Geod. Geophys., 52, 511–525, DOI: https://doi.org/10.1007/s40328-016-0186-0.
Duchnowski R. and Wiśniewski Z., 2017b. Msplit and MP estimation. A wider range of robustness. In: Vaiskunaite R. and Cygas D. (Eds), 10th International Conference on Environmental Engineering. Vilnius Gediminas Technical University Publishing House “Technika”, Vilnius, Lithuania, DOI: https://doi.org/10.3846/enviro.2017.185(http://enviro.vgtu.lt/index.php/enviro2017/2017/paper/viewFile/9/370).
Ge Y., Yuan Y. and Jia N., 2013. More efficient methods among commonly used robust estimation methods for GPS coordinate transformation. Surv. Rev., 45, 229–234.
Gui Q. and Zhang J., 1998. Robust biased estimation and its applications in geodetic adjustment. J. Geodesy, 72, 430–435.
Hampel F.R., 1974. The influence curve and its role in robust estimation. J. Am. Statist. Assoc., 69, 383–397.
Hampel F.R., Ronchetti E.M., Rousseuw P.J. and Stahel W.A., 1986. Robust Statistics. The Approach Based on Influence Functions. John Wiley & Sons, New York, NY.
Hekimoglu S. and Berber M., 2003. Effectiveness of robust methods in heterogeneous linear model. J. Geodesy, 76, 706–713.
Hekimoglu S. and Erenoglu R.C., 2013. A new GM-estimate with high breakdown point. Acta Geod. Geophys., 48, 419–137.
Huber P.J., 1964. Robust estimation of location parameter. Ann. Math. Statist., 43, 1041–1067.
Huber P.J., 1981. Robust Statistics. John Wiley & Sons, New York, NY.
Janicka J. and Rapinski J., 2013. Msplit transformation of coordinates. Surv. Rev., 45, 269–274.
Janowski A. and Rapinski J., 2013. Msplit estimation in laser scanning data modeling. J. Indian Soc. Remote Sens., 41, 15–19.
Jin Y., Tong X., Li L, Zhang S. and Liu S., 2015. Total least L1- and L2-norm estimations of a coordinate transformation model with a structured parameter matrix. Stud. Geophys. Geod., 59, 345–365.
Jones G.A. and Jones J.M., 2000. Information and Coding Theory. Springer Undergraduate Mathematics Series. Springer-Verlag, Berlin, Heidelberg, Germany.
Koch K.R., 1996. Robuste parameterschätzung. Allgemeine Vermessungsnachrichten, 103, 1–18.
Koch K.R., 2017. Expectation Maximization algorithm and its minimal detectable outliers. Stud. Geophys. Geod., 61, 1–18.
Kubik K., 1982. An error theory for the Danish method. In: Proceedings of the Symposium of the ISPRS Commission III Helsinki, 1982. XXIV-3, 299–309.
Krarup T. and Kubik K., 1983. The Danish method; experience and philosophy. Deutsche Geodätische Kommission bei der Bayerischen Akademie der Wissenschaften, München, Reihe A, Heft Nr 7, 131–134.
Lark R.M., 2008. Some results on the spatial breakdown point of robust point estimates of the variogram. Math. Geosci, 40, 729–751, DOI: https://doi.org/10.1007/s11004-008-9162-8.
Lehmann R., 2013. On the formulation of the alternative hypothesis for geodetic outlier detection. J. Geodesy, 87, 373–386.
Li J., Wang A. and Xinyuan W., 2013. Msplit estimate of the relationship between LS and its application in gross error detection. Mine Surveying, 2, 57–59, DOI: https://doi.org/10.3969/j.issn.1001-358X.2013.02.20 (in Chinese).
Militino A.F., 1997. M-estimator of the drift coefficients in a spatial linear model. Math. Geol., 29, 221–229.
Wang B., Li J. and Liu C., 2016. A robust weighted total least squares algorithm and its geodetic applications. Stud. Geophys. Geod., 60, 177–194.
Wiśniewski Z., 1996. Estimation of the third and fourth order central moments of measurement errors from sums of powers of least squares adjustment residuals. J. Geodesy, 70, 256–262.
Wiśniewski Z., 2009. Estimation of parameters in a split functional model of geodetic observations (Msplit estimation). J. Geodesy, 83, 105–120.
Wiśniewski Z., 2010. Msplit(q) estimation: estimation of parameters in a multi split functional model of geodetic observations. J. Geodesy, 84, 355–372.
Wiśniewski Z., 2014. M-estimation with probabilistic models of geodetic observations. J. Geodesy, 88, 941–957.
Wiśniewski Z. and Zienkiewicz M.H., 2016. Shift-M*split estimation in deformation analyses. J. Surv. Eng., 142, 1–13.
Xu P., 2005. Sign-constrained robust least squares, subjective breakdown point and the effect of weights of observations on robustness. J. Geodesy, 79, 146–159.
Yang Y., 1992. Robustifying collocation. Manuscr. Geod., 17, 21–28.
Yang Y., 1994. Robust estimation for dependent observations. Manuscr. Geod., 19, 10–17.
Yang Y., 1997. Estimators of covariance matrix at robust estimation based on influence functions. Z. Vermessungswesen, 122, 166–174.
Yang Y., 1999. Robust estimation of geodetic datum transformation. J. Geodesy, 73, 268–274.
Yang Y., Cheng M.K., Shum C.K. and Tapley B.D., 1999. Robust estimation of systematic errors of satellite laser range. J. Geodesy, 73, 345–349.
Yang Y., He H. and Xu G., 2001. Adaptively robust filtering for kinematic geodetic positioning. J. Geodesy, 75, 106–109.
Yang Y., Gao W. and Zhang X., 2010. Robust Kalman filtering with constraints: a case study for integrated navigation. J. Geodesy, 84, 373–381.
Zhang J. and Li G., 1998. Breakdown properties of location M-estimators. Ann. Statist., 26, 1170–1189.
Zhong D., 1997. Robust estimation and optimal selection of polynomial parameters for the interpolation of GPS geoid heights. J. Geodesy,71, 552–561.
Zhuo D., 1987. Robust statistics and geochemical data analysis. Math. Geol., 19, 207–218.
Zienkiewicz M.H., 2015. Application of Msplit estimation to determine control points displacements in networks with unstable reference system. Surv. Rev., 47, 174–180.
Zienkiewicz M.H. and Baryła R., 2015. Determination of vertical indicators of ground deformation in the old and main city of Gdansk area by applying unconventional method of robust estimation. Acta Geodyn. Geomater., 12, No.3(179), 249–257.
Zuo Y., 2006. Robust location and scatter estimators in multivariate analysis. In: Fan J. and Koul H.L. (Eds), Frontiers of Statistics, Part VII. Parametric Techniques and Inferences, 467–490. Imperial College, London, U.K., DOI: https://doi.org/10.1142/9781860948886_0021.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Duchnowski, R., Wiśniewski, Z. Robustness of Msplit(q) estimation: A theoretical approach. Stud Geophys Geod 63, 390–417 (2019). https://doi.org/10.1007/s11200-018-0548-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11200-018-0548-x