New Wald-Type Estimation Procedures for fitting Structural Measurement Error Model


Abstract


This article proposes a new estimation method to fit the structural regression model when the variables are subject to errors. The new estimation method is the extension of the Wald estimation method and involves iterative process. Several Monte Carlo simulation experiments were used to study the performance of the proposed estimators. The results were compared with the classical Wald estimation method in terms of its root mean square error (RMSE). In addition, an application for examining the relationships between Jordan’s national gross domestic product (GDP) and its human development index (HDI) was presented. Numerical results showed that the GDP and HDI have a strong positive and significant correlation. Moreover, the proposed procedures with different subgroup sizes (r =3 and r =4) gave more accurate estimators than the classical estimation methods in fitting the relationships between GDP and HDI.


DOI Code: 10.1285/i20705948v16n2p487

Keywords: Measurement Error Models, Wald Estimator, Repetitive Estimator, Human Development Index, National Gross Domestic Product, Monte Carlo Simulation

Full Text: pdf
کاغذ a4

Creative Commons License
This work is licensed under a Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia License.