The maximum likelihood estimation for multivariate EIV model
- 23 Downloads
In this paper, a new method of parameter estimation for multivariate errors-in-variables (MEIV) model was proposed. The formulae of parameter solution for the MEIV model were deduced based on the principle of maximum likelihood estimation, and two iterative algorithms were presented. Since the iterative process is similar to the classical least square, both of the proposed algorithms are easy to program and understand. Finally, real and simulation datasets of affine coordinate transformation were employed to verify the applicability of the proposed algorithms. The results show that both of the proposed algorithms can achieve identical parameter estimators as those obtained by Lagrange algorithm and Newton algorithm. Additionally, the proposed Algorithm 2 can solve the MEIV model with higher convergence efficiency than Algorithm 1.
KeywordsTotal least squares Multivariate errors-in-variables model Parameter estimation Iterative algorithm
This research was supported by the Natural Science Foundation of Hunan Province (No.2017JJ5035) and the Natural Science Foundation of Jiangsu Province (No. BK20180720).
Compliance with ethical standards
Conflicts of interest
The authors declare no conflict of interest.
- Amiri-Simkooel AR, Jazaeri S (2012) Weighted total least squares formulated by standard least squares theory. J Geod Sci 2(2):113–124Google Scholar
- Fang X (2011) Weighted total least squares solutions for applications in geodesy. Ph.D. Thesis. Leibniz University, Hannover, GermanyGoogle Scholar
- Schaffrin B, Felus YA (2008a) On the multivariate total least-squares approach to empirical coordinate transformations. Three algorithms. J Geod 82:372–383Google Scholar
- Schaffrin B, Felus Y (2008b) Multivariate total least-squares adjustment for empirical affine transformations. In: Xu P, Liu J, Dermanis A (eds) VI Hotine-Marussi symposium on theoretical and computational geodesy international association of geodesy symposia, 29 May–2 June, Wuhan, China, vol 132, pp 238–242. Springer, BerlinGoogle Scholar
- Schaffrin B, Wieser A (2009) Empirical affine reference frame transformations by weighted multivariate TLS adjustment. Geodetic reference frames. Springer, Berlin, pp 213–218Google Scholar
- Wang L, Zhao YW, Chen XY, Zang DY (2016b) A Newton algorithm for multivariate total least squares problems. Acta Geodaetica Cartogr Sin 45:411–417 (in Chinese with English Abstract) Google Scholar