dc.contributor.author |
Karaibrahimoglu, Adnan |
|
dc.contributor.author |
Asar, Yasin |
|
dc.contributor.author |
Genc, As?r |
|
dc.date.accessioned |
2018-07-29T10:53:03Z |
|
dc.date.available |
2018-07-29T10:53:03Z |
|
dc.date.issued |
2016 |
|
dc.identifier.issn |
1815-3852 |
|
dc.identifier.uri |
https://journal.uob.edu.bh:443/handle/123456789/1117 |
|
dc.description.abstract |
In multiple linear regression analysis, multicollinearity is an important problem. Ridge regression is one of the most commonly used methods to overcome this problem. There are many proposed ridge parameters in the literature. In this paper, we propose some new modifications to choose the ridge parameter. A Monte Carlo simulation is used to evaluate parameters. Also, biases of the estimators are considered. The mean squared error is used to compare the performance of the proposed estimators with others in the literature. According to the results, all the proposed estimators are superior to ordinary least squared estimator (OLS). |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
University of Bahrain |
en_US |
dc.rights |
Attribution-NonCommercial-ShareAlike 4.0 International |
* |
dc.rights.uri |
http://creativecommons.org/licenses/by-nc-sa/4.0/ |
* |
dc.subject |
Multicollinearity |
|
dc.subject |
Multiple linear regression |
|
dc.subject |
Ridge regression |
|
dc.subject |
Ridge estimator |
|
dc.subject |
Monte Carlo simulation |
|
dc.title |
Some new modifications of Kibria’s and Dorugade’s methods: An application to Turkish GDP data |
en_US |
dc.type |
Article |
en_US |
dc.source.title |
Arab Journal of Basic and Applied Sciences |
|
dc.abbreviatedsourcetitle |
AJBAS |
|