Naslov
Forecasting housing affordability in selected post-transition economies

Autori
Dumičić, Ksenija ; Žmuk, Berislav ; Čeh Časni ; Anita

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, ostalo

Izvornik
Book of Abstracts of the Economic and Social Development (ESD), 5th Eastern European Economic and Social Development Conference on Social Responsibility, Belgrade, Serbia, May 21-22, 2015 / Jovancai Stakic, Ana ; Kovsca, Vladimir ; Bendekovic, Jadranka - Varaždin : VADEA, 2015, 21-22

Skup
5th Eastern European Economic and Social Development Conference on Social Responsibility, Belgrade, Serbia, May 21-22, 2015

Mjesto i datum
Beograd, Srbija, 21.05.2015. - 22.05.2015

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
forecasting models ; housing affordability ; indicators ; measures of forecasting accuracy ; post-transition countries

Sažetak
In this research housing affordability as a measure of population's ability to afford or to purchase a particular item, such as a house, indexed to the population's income is investigated. The main aim of this research was to forecast housing affordability in three selected post-transition economies: Croatia, Latvia and Serbia. Overall, five indicators of housing affordability are studied: Price to income ratio ; Gross rental yield city centre ; Gross rental yield outside of centre ; Mortgage as a percentage of income and Affordability index. Due to data deficiency, the values of aforementioned indicators are analysed for the period from 2009 to 2015, based on yearly data, and only short-term forecasts are conducted. NUMBEO database was used as data source. In order to determine short-term future trends of change in these indicators, six forecasting models were applied, namely: naïve model I, naïve model II, naïve model IIa, geometric mean forecasting model, simple average forecasting model and single exponential smoothing model. The best forecasting model for each indicator and for each country is selected according to the Mean Absolute Percentage Error (MAPE) criterion. The forecasting model with the lowest MAPE value is used to determine the trend based forecast of housing affordability. According to the research results, housing affordability level, in general, is likely to rise in Croatia. Furthermore, there is high probability that housing affordability in Latvia is going to increase in the next years. In contrast, housing affordability in Serbia is most likely to decrease in the following period.

Izvorni jezik
Engleski

Znanstvena područja
Ekonomija

Napomena
Ovaj rad je u potpunosti podržan od strane Hrvatske zaklade za znanost kao dio znanstvenog projekta „Statistical Modelling for Response to Crisis and Economic Growth in Western Balkan Countries“ (STRENGTHS) ; Broj projekta: HRZZ-IP-2013-11-9402. Voditeljica: prof. dr. sc. Ksenija Dumičić

POVEZANOST RADA