Academic journal article Global Journal of Business Research

Forecasting Real Estate Business: Empirical Evidence from the Canadian Market

Academic journal article Global Journal of Business Research

Forecasting Real Estate Business: Empirical Evidence from the Canadian Market

Article excerpt

ABSTRACT

In this paper, we compare the out-of-sample forecasting ability of three ARIMA family models: ARIMA, ARIMAX, and ARIMAX-GARCH. The models are tested to forecast turning points and trends in the Canadian real estate index using monthly data from April 2002 to March 2011. The results indicate that the ARIMAX model, which includes exogenous macroeconomic variables such as the gross domestic product, the consumer price index, the difference in long-term and short-term interest rates, and the exchange rate of the Canadian dollar against the US dollar and their lags, provides the best out-of-sample forecasts. Overall, the models are suitable only for short-term forecasts.

JEL:R3,G01,O51,C53

KEYWORDS: Real Estate, Financial Crisis, Canada, ARIMAX, GARCH

(ProQuest: ... denotes formulae omitted.)

INTRODUCTION

Since the 2008 financial crisis, the world markets have gone through much uncertainty, and even after four years of crisis, the markets are unstable. The crisis led many economists to probe the nature and causes: low interest rates, high interest rates, mortgage-backed securities, asset-backed securities, credit default swaps, bad regulations, cheating, etc. However, the real estate market played a central role, bringing real estate issues before policymakers. The real estate industry is unique in terms of its contribution to a country's gross domestic product (GDP) and the overall impact on economy. At the same time, the real estate market is inefficient and illiquid, and faces regular intervention by governments across the world. Hence, the movement of the real estate business becomes a key ingredient in planning for the layperson, investors, and policymakers.

Although much research is available for the US market, research on the Canadian real estate market is unavailable. Though the Canadian market is very similar to the US market in most cases, the Canadian real estate market has several different features. The Canadian real estate market was not hurt by the financial crisis compared to the US real estate market, which is still struggling to recover. In contrast, the Canadian real estate market has increased since the beginning of 2009. In terms of broader differences, the average Canadian saw his or her income grow, and the Canadian banking structure imposes uniform and stable interest rates. These factors suggest that other factors played a role in the real estate market. This study tests a simple and widely available model to assist the common forecaster. In particular, the study uses the time series auto regressive integrated moving average (ARIMA), and then uses the auto regressive integrated moving average with exogenous variables (ARIMAX) and the auto regressive integrated moving average with exogenous variables including generalized auto regressive conditional heteroskedastic (ARIMAX-GARCH) models to test their forecasting capability.

To understand the nature of the Canadian real estate market, this study uses a times series model with a macroeconomic variable in line with other studies such as those Brooks and Tsolocas (1999), De Wit and Van Dijk (2003), and Karakozova (2004), who found the effect of the macroeconomic variable on real estate. This paper contributes significantly to the existing real estate literature by adding knowledge of Canadian real estate and its connection with macroeconomic variables and presenting a simple tool for forecasters.

Researchers have applied various models to explain the real estate market, from simple linear regression to advanced models such as the Vector Error Correction model (VECM), the Kaiman filter, and so on. However, in the end simple models were found efficient compared to more complex models (Wilson, Ellis, Okunew and Higgins, 2000, Crawford and Fratantoni, 2003, Stevenson and Young, 2007). Thus, this paper focuses on the performance of univariate models. Moreover, the purpose of this study is to provide a simple tool to forecasters. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed

Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.