The Generalized Estimating Equations for the Unknown Correlation Structure of the Data

Authors

  • Md. Soyebur Rahman

Keywords:

generalized estimating equation, GEE, OLS, GLM

Abstract

In many study the data are taken different period of time and the information about them is gathered relating to an event of concern at different time periods. The data are taken different time period are correlated. Regression analysis based on the Generalized Estimating Equation (GEE) is an increasing important method of such data. The Generalized Estimating Equation is an important and widely used approach in such analysis. Since the true correlation is unknown GEE offers to take a working correlation for analysis. In our study we consider four common correlation structure namely, independent, exchangeable, pair wise, autoregressive. In the study the data are taken from the Dhaka stock exchange (DSE) this data are highly correlated. At first we apply different methods of estimating parameter the we apply GEE for estimating the parameters. Finally we get the GEE gives better estimate than any other method.

How to Cite

Md. Soyebur Rahman. (2016). The Generalized Estimating Equations for the Unknown Correlation Structure of the Data. Global Journal of Computer Science and Technology, 16(G1), 21–22. Retrieved from https://computerresearch.org/index.php/computer/article/view/1420

The Generalized Estimating Equations for the Unknown Correlation Structure of the Data

Published

2016-01-15