THE IMPACT OF HANDLING MISSED DATA ON THE GAMMA REGRESSION RESPONSE | ||||
المجلة العلمية للدراسات والبحوث المالية والتجارية | ||||
Article 13, Volume 5, Issue 1, January 2024, Page 273-303 PDF (898.79 K) | ||||
Document Type: المقالة الأصلية | ||||
DOI: 10.21608/cfdj.2024.324098 | ||||
View on SCiNiTO | ||||
Author | ||||
Amira Eldesokey | ||||
cairo, Egypt | ||||
Abstract | ||||
This paper presents a comprehensive comparison of various missing data approaches in gamma regression analysis. The study evaluates the performance of linear trend at point method, mean imputation method, and three multiple imputation methods (KNN, PMM, and EM) in handling missing data at different positions (top, center, and bottom) of the data range. The maximum likelihood estimation technique is employed to estimate the parameters of the gamma regression model. An empirical example is presented to demonstrate the application of these methods in analyzing factors affecting carbon dioxide emission in Egypt. The findings reveal that multiple imputation methods outperform other approaches in terms of accuracy and precision. This study provides valuable insights into how different missing data techniques can be utilized to enhance the accuracy and precision of gamma regression models. The results have important implications for researchers and practitioners who use gamma regression analysis to investigate various phenomena with missed data. | ||||
Keywords | ||||
Gama Regression; Maximum Likelihood; missing data; linear trend at point method; mean imputation method; K- Nearest Neighbor Method (KNN); Predictive Mean Matching (PMM); Expectation Maximization Imputation (EM) | ||||
Statistics Article View: 40 PDF Download: 58 |
||||