Beta Regression for the Indicator Values of Well-Being Index For Provinces in Turkey

Authors : Hande ÜNLÜ, Serpil AKTAŞ

Pages : 101-111

Doi:10.30931/jetas.321165

View : 13 | Download : 20

Publication Date : 2017-10-09

Article Type : Research Paper

Abstract :Beta regression assumes that the dependent variable follows a beta distribution and that its mean is related to a set of exploratory variables through a linear predictor with unknown coefficients and a link function. The model also includes a dispersion parameter. This paper describes the beta regression model along with its properties. The application of the model is made on well-being index data of Turkey 2015, which comprise the dimensions of housing, work, income and wealth, health, education, environment, safety, civic participation and access to infrastructure services and social life. As the life satisfaction index lies between 0 and 1 and the values close to 1 refers to a better level of life. Beta regression fits the data well and the regression parameters are well interpreted in terms of the mean of the response variable.
Keywords : beta distribution, beta regression, dispersion parameter