Generalized Least Square Estimation of Error-in-Variable Models and its Statistical Property

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 154)


People often meet various errors in dealing with practical problems. These errors can cause a lot of inconvenience. Especially when dependent and independent variables contain errors, people must pay special attention to it. Error-in-Variable Models can handle the situation. This paper got the conclusion that Generalized Least Square Estimate is better than Least Square Estimate under the condition of not independence between samples by analyzing pitman superiority.


Structural Relation Structure Matrix Invertible Matrix Order Identity Inequality Sign 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wang Songgui. Linear model theory and its application Linear model theory and its application. Hefei: Anhui education press, Anhui education press, 1987: 50–68.Google Scholar
  2. 2.
    Chen Xiru, Wang Songgui. The Least Squares in the linear model. Shanghai science and technology press, Shanghai science and technology, 2003Google Scholar
  3. 3.
    Li Yong, Tang Shouzheng. Generalized Linear Error-in-Variable Model. Chinese Journal of Applied Probability and Statistics, 2006, 22(1): 81–88.Google Scholar
  4. 4.
    Dolby G R. The ultra structural relation: A synthesis of the functional and structural relations. Biometrica, 1976, 63(2): 39–50.Google Scholar
  5. 5.
    Wang Songgui,Yang Zhenghai. The Pitman Superiority of covariance improvement estimate. Chinese Science Bulletin, 1995, 40(1): 12–16.Google Scholar

Copyright information

© Springer-Verlag London Limited 2012

Authors and Affiliations

  1. 1.Department of MathematicsYangtze Normal UniversityChongqingChina

Personalised recommendations