Regularization of Bayesian quasi-likelihoods constructed from complex estimating functions

2020 ◽  
Vol 150 ◽  
pp. 106977
Author(s):  
Ray S.W. Chung ◽  
Mike K.P. So ◽  
Amanda M.Y. Chu ◽  
Thomas W.C. Chan
Keyword(s):  
Estimating Functions

PG-less Vector Control with Estimating Functions of Motor Parameter.

1991 ◽  
Vol 111 (5) ◽  
pp. 373-378 ◽  
Author(s):  
Naoki Yamamura ◽  
Masahiko Iwasaki ◽  
Hirotaka Sakurai ◽  
Yuzuru Tunehiro
Keyword(s):  
Vector Control ◽  
Estimating Functions ◽  
Motor Parameter

Combining estimating functions for volatility

2009 ◽  
Vol 139 (4) ◽  
pp. 1449-1461 ◽  
Author(s):  
M. Ghahramani ◽  
A. Thavaneswaran
Keyword(s):  
Estimating Functions

Restricted quasi-score estimating functions for sample survey data

2004 ◽  
Vol 41 (A) ◽  
pp. 119-130
Author(s):  
Y.-X. Lin ◽  
D. Steel ◽  
R. L Chambers
Keyword(s):  
Maximum Likelihood ◽  
Survey Data ◽  
Sample Survey ◽  
Likelihood Method ◽  
Sample Surveys ◽  
Estimating Functions ◽  
Limit Theory ◽  
Normal Probability ◽  
Probability Structure ◽  
Sample Survey Data

This paper applies the theory of the quasi-likelihood method to model-based inference for sample surveys. Currently, much of the theory related to sample surveys is based on the theory of maximum likelihood. The maximum likelihood approach is available only when the full probability structure of the survey data is known. However, this knowledge is rarely available in practice. Based on central limit theory, statisticians are often willing to accept the assumption that data have, say, a normal probability structure. However, such an assumption may not be reasonable in many situations in which sample surveys are used. We establish a framework for sample surveys which is less dependent on the exact underlying probability structure using the quasi-likelihood method.

scholarly journals Estimasi Fungsi Regresi Dalam Model Regresi Nonparametrik Birespon Menggunakan Estimator Smoothing Spline dan Estimator Kernel

2018 ◽  
Vol 15 (2) ◽  
pp. 20 ◽  
Author(s):  
Budi Lestari
Keyword(s):  
Regression Model ◽  
Nonparametric Regression ◽  
Kernel Estimator ◽  
Regression Function ◽  
Predictor Variables ◽  
Smoothing Spline ◽  
Estimating Functions ◽  
Nonparametric Regression Model ◽  
Estimation Techniques ◽  
Connection Pattern

Abstract Regression model of bi-respond nonparametric is a regression model which is illustrating of the connection pattern between respond variable and one or more predictor variables, where between first respond and second respond have correlation each other. In this paper, we discuss the estimating functions of regression in regression model of bi-respond nonparametric by using different two estimation techniques, namely, smoothing spline and kernel. This study showed that for using smoothing spline and kernel, the estimator function of regression which has been obtained in observation is a regression linier. In addition, both estimators that are obtained from those two techniques are systematically only different on smoothing matrices. Keywords: kernel estimator, smoothing spline estimator, regression function, bi-respond nonparametric regression model. AbstrakModel regresi nonparametrik birespon adalah suatu model regresi yang menggambarkan pola hubungan antara dua variabel respon dan satu atau beberapa variabel prediktor dimana antara respon pertama dan respon kedua berkorelasi. Dalam makalah ini dibahas estimasi fungsi regresi dalam  model regresi nonparametrik birespon menggunakan dua teknik estimasi yang berbeda, yaitu smoothing spline dan kernel. Hasil studi ini menunjukkan bahwa, baik menggunakan smoothing spline maupun menggunakan kernel, estimator fungsi regresi yang didapatkan merupakan fungsi linier dalam observasi. Selain itu, kedua estimator fungsi regresi yang didapatkan dari kedua teknik estimasi tersebut secara matematis hanya dibedakan oleh matriks penghalusnya.Kata Kunci : Estimator Kernel, Estimator Smoothing Spline, Fungsi Regresi, Model Regresi Nonparametrik Birespon.

Estimation of Strength Parameters and Finite Element Simulation of Lime and Cement Stabilized Granular Soils

2013 ◽  
Vol 681 ◽  
pp. 276-280 ◽  
Author(s):  
Omid Azadegan ◽  
Jie Li ◽  
Hadi Jafari
Keyword(s):  
Finite Element ◽  
Laboratory Experiments ◽  
Test Procedure ◽  
Granular Soils ◽  
Estimating Function ◽  
Estimating Functions ◽  
Shear Strength Parameters ◽  
Strength Parameters ◽  
Element Simulation ◽  
Study Results

Finite element modeling of stabilized soils requires various data obtained from comprehensive laboratory experiments. High shear strengths and expensive test procedure of lime and cement stabilized soils almost make it impossible to attain a well describing data of stabilized materials to apply in FE models in some cases; Thus, this study has considered unconfined compressive strength as a not expensive laboratory strength test and utilized estimating functions presented recently for stabilized materials to evaluate the shear strength parameters of treated materials to be used in computer simulations. The estimated properties were applied in FE modeling to verify which estimating function is more appropriate for lime and cement treated granular soils. The study results show that at the mid-range strength of stabilized soils most of applied functions have a good compatibility with laboratory conditions but at lower or higher strengths some of functions would excel.

Sign in / Sign up

Export Citation Format

Share Document