Calibration Estimation via a Smoothing Newton Method
نویسنده
چکیده
Calibration estimation is currently the most popular method of estimation using auxiliary information. Its major idea is to use auxiliary information to structure calibration weights, attaching them to survey data, in order to improve the accuracy of the gross or mean estimation. Calibration estimation problem with box constraints is equivalently to solve a nonlinear equations system. Mnnich at el proposed a semismooth Newton method for solving this system in [Calibration of estimator -weights via semismooth Newton Method. J. Glob. Optim. 52 (2012):471-485]. In this paper, we give more specific analysis about the semismooth Newton method and some numerical experiments have been reported. On the basis of that, a smoothing Newton method has been proposed and proved to be globally convergent without any assumptions and locally superlinearly convergent under certain assumptions. Numerical results show that both semismooth Newton method and smoothing Newton method are effect for solving the calibration estimation problem. Key–Words: Calibration estimation; Auxiliary information; Sample weights; Semismooth Newton method; Smoothing Newton method; Global convergence
منابع مشابه
Development of near infrared reflectance spectroscopy (NIRS) calibration model for estimation of oil content in a worldwide safflower germplasm collection
The development of NIRS calibration model as a rapid, precise, robust, and cost-effective method to estimate oil content in ground seeds of worldwide safflower germplasm collection grown under different agro-climatic conditions was the key objective of this research project. The oil content was measured by accelerated solvent extraction method in a total of 328 samples collected across 2004 (16...
متن کاملMinimizing GCV/GML Scores with Multiple Smoothing Parameters via the Newton Method
The (modified) Newton method is adapted to optimize generalized cross validation (GCV) and generalized maximum likelihood (GML) scores with multiple smoothing parameters. The main concerns in solving the optimization problem are the speed and the reliability of the algorithm, as well as the invariance of the algorithm under transformations under which the problem itself is invariant. The propos...
متن کاملAn Improved Spatial Smoothing Technique for DoA Estimation of Highly Correlated Signals
Spatial superresolution techniques have been investigated for several decades in many fields: Communication, radar, sonar, etc. One of the most investigated techniques is multiple signal classification (MUSIC) algorithm. Its simplicity has made it very attractive in such fields. However, the main drawback of this algorithm lies on its failure to resolve coherent/highly correlated signals. Many ...
متن کاملReview and Comparison of In-field Calibration Methods of Accelerometer Based on Gravity Vector
Considering the wide applications of accelerometers to determine position and attitude and due to reducing of accuracy of this sensors because of some errors, this paper discusses the calibration of accelerometers. Also because the traditional calibration methods are very time consuming, costly and need precision laboratory equipment, in-field calibration methods are recommended which are simpl...
متن کاملSolving Log-Determinant Optimization Problems by a Newton-CG Primal Proximal Point Algorithm
We propose a Newton-CG primal proximal point algorithm for solving large scale log-determinant optimization problems. Our algorithm employs the essential ideas of the proximal point algorithm, the Newton method and the preconditioned conjugate gradient solver. When applying the Newton method to solve the inner sub-problem, we find that the log-determinant term plays the role of a smoothing term...
متن کامل