Estimate the Parameters of Sigmoidal Growth Models by Using Bayesian Method | ||
| The Egyptian Statistical Journal | ||
| Article 6, Volume 57, Issue 1, June 2013, Pages 1-17 PDF (15.24 M) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/esju.2013.314347 | ||
| Authors | ||
| Abdullah Suleiman Mahmoud* 1; Saif al-Din Hashim Qamar2 | ||
| 1Taif University, Kingdom of Saudi Arabia | ||
| 2College of Administration and Economics, University of Iraq | ||
| Abstract | ||
| Bayesian approach is the most important methods that used in the statistical analysis, so we have studied in paper this approach by using two of the Sigmoidal growth models, where those models are more using to represent the growth phenomena. The researchers focused on three of prior functions (Informative, Natural Conjugate, and the function that depends on previous experiments) to use it in the Bayesian method. The goal of this study is to estimate the parameters of the growth models by using Bayesian method, and compare it with the Least squares method. For verifying the goal has been used the simulation technique where generated random samples with known parameters. It has been shown from the computational results that the Bayesian method is better than the Least squares method to estimate the Sigmoidal growth models. | ||
| Keywords | ||
| Growth Curve; Sigmoidal - Logistic Model - Gompertz Model - Bayesian | ||
|
Statistics Article View: 87 PDF Download: 10 |
||
