The comparison of the efficiency and biasedness of Ridge and Liu estimators
2011
0 views
0 downloads
Advisor: Doç. Dr. Berna Yazıcı
Abstract (EN)
One of the problems encountered in the multipregression analysis is multicollinearity case. The multicollinearity problem occurs if one or more independent variables are explained by other indepented variables. Biased estimation methods are commonly used in order to remove or reduce multicollinearity. In this study, the comparison of Ridge and Liu estimators which are known as biased estimation methods is given. Firstly the two methods have been defined and then applied on a data set about ? The tourism income in Turkey between 1985 and 2006?. To explain that dependent variable those six variables are used: Total bed amount, the number of foreign tourist, the number of tourism agecies, the amount of foreign investment, the exchange rate of Euro and the exchange rate of US dollars. Finally the two methods are compared with each other in terms of their efficiency and their biasedness and the results are interpreted.Keywords: Multicollinearity, Ridge Estimators, Liu Estimators, Biased Estimation Methods, Tourism Income
Author
Dr. Emine Karakaya
How to Cite
Emine Karakaya (Master Thesis). The comparison of the efficiency and biasedness of Ridge and Liu estimators, 2011, Anadolu University.
Keywords
License
Tüm Hakları Saklıdır
This work is shared under the specified license terms.
More theses from Anadolu University
- Morphological, anatomical and phytochemical studies on Fritillaria imperialis L. and Fritillaria persica L.(2019)
- Religious architecture of Adana in Byzantine Period(2021)
- Animation and magical realism(2021)
- The effectiveness of teaching to safety travel skills by fasten seat belt using social stories to individuals with intellectual disabilities(2021)
- Investigation the expectations and experiences of parents about speech and language therapy"(2021)
- An analysis of the cello techniques used by Henri Dutilleuxin his work Trois Strophes Sur Le Nom de Sacher(2021)
