Abstract
Regression analyses look at how the answer variable and one or more explanatory factors are related. When the explanatory variables are linearly dependent, it becomes practically difficult to model this relationship in real-world applications. Several shrinkage estimators are suggested traditionally to avoid this problem. When there is linear dependency between the explanatory variables, one of the most widely used estimate techniques is the ridge estimator. In this paper, we suggested a jackknifed variant of the ridge estimator to reduce biasedness for the Bell regression model.The simulation results demonstrated that the proposed method is able to effectively outperform other alternatives estimators in terms of mean squarederror (MSE). Further, the application results, which are based on two datasets: aircraft data and mine fracture data showed that the suggested estimator improves the ridge estimator's performance in terms of MSE
Recommended Citation
Algamal, Zakariya Yahya; Lukman, Adewale F.; Kibria, B. M Golam; and Taofik, Arowolo Olatunji
(2023)
"Modified Jackknifed Ridge Estimator in Bell Regression Model: Theory, Simulation and Applications,"
Iraqi Journal for Computer Science and Mathematics: Vol. 4:
Iss.
1, Article 14.
DOI: https://doi.org/10.52866/ijcsm.2023.01.01.0012
Available at:
https://ijcsm.researchcommons.org/ijcsm/vol4/iss1/14
