Estimating of probability of home-ownership in rural and urban areas: Logit, probit and Gompit model

Abstract

This study examines various factors affecting probability of home ownership in Turkey for both urban and rural areas separately. We use three different binary dependent variable models which are named as Logit, Probit and Gompit and compare them to determine the best model. The findings show that Logit model is the best model to determine the probability of home-ownership for both urban and rural areas. Factors which influence the probability of home-ownership in urban areas were determined to be income, age, gender, education, marital status, employment status of the household head, and the type of house. While there is no such variable as gender and marital status within factors which influence the probability of home-ownership in rural areas, the variable of being insured was included.