Monte - Carlo evaluation of power transformations in regression model
Is this your thesis?
This record came from a bulk archive import. If it’s yours, link it to your profile.
Abstract (EN)
In the classical regression model, it is assumed that the error terms are independently, identically and normally distributed. In this study, the cases where the assumptions of normality and homoskedasticity are not valid were modelled and the performances of the power transformations were compared by a Monte-Carlo virtual experiment. The results showed that Tukey's transformation and Manly's transformation performed better than others, respectively in case of the departure from normality and from homoskedasticity. Science Code : 212 Key Words Regression; power transformation; Monte-Carlo estimation Page Number : 64 Adviser : Ass. Prof. Dr. Mustafa Yavuz ATA
Author
Hüseyin Güler
How to Cite
Hüseyin Güler (Master Thesis). Monte - Carlo evaluation of power transformations in regression model, 2004, Gazi University.
Keywords
License
Tüm Hakları Saklıdır
This work is shared under the specified license terms.
More theses from Gazi University
- Experimental development of the interfacial bond-slip model between textile reinforced mortar strips and masonry walls(2025)
- Occupational accident analysis and modelling in oil and gas drilling sector Turkey(2021)
- XVI. yüzyıl Anadolu'sunda Oğuzların Karkın Boyu(2004)
- The ideological construction of regime debate in Turkey by the press in the context of 2007 presidential elections(2012)
- Sharing of real life geometry samples via a social learning environment: A case study(2021)
- The use of verbal memory in the context of sustainability and power at the museums of Turk(2010)