Clustering and panel data analysis in the study of housing sales in provincial groups of turkey

Housing demand arises from social, cultural, economic and demographic characteristics of a country. The rapid transformation process in the housing sector of Turkey and change in factors affecting housing demand constitute systematic risk in terms of its structure. These risks necessitate a closer monitoring of market indicators and more scientific research in this area. Recently, many evaluations on the housing sector in Turkey are seen to be taking place both in the media and in different organizations. It is aimed to examine and share a sectoral analysis in order to be very different from each other and to affect all socioeconomic factors. The sample of the research; the number of annual housing sales and the factors affecting housing sales of the provinces of Turkey in the 2008-2015 process. In this thesis study; balanced panel data analysis and clustering analysis methods were applied to the factors affecting housing demand of provincial groups of Turkey. The main purpose of the study is to determine the provinces with similar characteristics in the demand for housing and the factors affecting housing demand. Findings indicate that housing price index, gross domestic product, average household income, housing gross return ratio, number of migration inflow and outflow, marriage and divorce all have significant effects on housing demand. Keywords: Housing demand, panel data analysis, clustering method, Turkey.