Third-Order Efficiency of the Extended Maximum Likelihood Estimators in a Simultaneous Equation System

Econometrica ◽  
1985 ◽  
Vol 53 (1) ◽  
pp. 177 ◽  
Author(s):  
Kei Takeuchi ◽  
Kimio Morimune
1989 ◽  
Vol 5 (3) ◽  
pp. 385-404 ◽  
Author(s):  
Yuzo Hosoya ◽  
Yoshihiko Tsukuda ◽  
Nobuhiko Terui

The concepts of the curved exponential family of distributions and ancillarity are applied to estimation problems of a single structural equation in a simultaneous equation model, and the effect of conditioning on ancillary statistics on the limited information maximum-likelihood (LIML) estimator is investigated. The asymptotic conditional covariance matrix of the LIML estimator conditioned on the second-order asymptotic maximal ancillary statistic is shown to be efficiently estimated by Liu and Breen's formula. The effect of conditioning on a second-order asymptotic ancillary statistic, i.e., the smallest characteristic root associated with the LIML estimation, is analyzed by means of an asymptotic expansion of the distribution as well as the exact distribution. The smallest root helps to give an intuitively appealing measure of precision of the LIML estimator.


GIS Business ◽  
2016 ◽  
Vol 11 (6) ◽  
pp. 28-38
Author(s):  
Dinis Daniel Santos ◽  
Elias Soukiazis

This work uses a simultaneous equation system approach to analyze the relationship between the management and business quality of companies and their market price quality. Using panel data we found that both the management and the business quality of companies positively influence the market price quality of the studied American companies. Additionally, variables like the actual position of the company price quality compared to the industry average, being on the top or the bottom, or the beta value of a company, also influence the market price quality of the respective company. It is shown that the system equation approach is the most appropriate to explain the linkages between price, business, and management quality providing consistent estimates. Also, using ratings to express the three core variables in the system is the most adequate way to define the quality characteristics in terms of price, management, and business performance of the companies considered in this study.


2015 ◽  
Vol 22 (1) ◽  
pp. 20-41
Author(s):  
Bao Nguyen Hoang

Although Vietnam’s economic growth and poverty reduction for almost three decades have been remarkable, growth for poverty reduction is unequally distributed across the nation. The paper examines the cause of poverty and the impact of provincial economic growth on poverty alleviation, using the data of 63 provinces in Vietnam. The elasticity of poverty with respect to provincial economic growth is employed (the elasticities of headcount index, poverty gap index, and squared poverty index with respect to provincial economic growth) to identify the provinces where pro-poor growth has occurred. The elasticity of poverty with respect to provincial Gini coefficient is examined to identify the impact of expenditure inequality on poverty. The simultaneous equation system is estimated to analyze not only direct and indirect effects of the related variables, but also the causality effect between economic growth and the poverty elasticity with respect to both growth and the Gini coefficient.


1986 ◽  
Vol 2 (1) ◽  
pp. 1-32 ◽  
Author(s):  
T. W. Anderson ◽  
Naoto Kunitomo ◽  
Kimio Morimune

Comparisons of estimators are made on the basis of their mean squared errors and their concentrations of probability computed by means of asymptotic expansions of their distributions when the disturbance variance tends to zero and alternatively when the sample size increases indefinitely. The estimators include k-class estimators (limited information maximum likelihood, two-stage least squares, and ordinary least squares) and linear combinations of them as well as modifications of the limited information maximum likelihood estimator and several Bayes' estimators. Many inequalities between the asymptotic mean squared errors and concentrations of probability are given. Among medianunbiasedestimators, the limited information maximum likelihood estimator dominates the median-unbiased fixed k-class estimator.


Sign in / Sign up

Export Citation Format

Share Document