A Comparative Study to Select the Best Model for Realistic Housing Unit Price Determination

Paul Boye, Daniel . Mireku-Gyimah

Abstract


The aim of this paper is to compare the following developed models: Multiple Linear Regression Model (MLRM), Principal Components Regression Model (PCRM) and Time Series Analysis Model (TSAM) that could be used to determine realistic Housing Unit Price (HUP) for one-bedroom and two-bedroom housing units. The motive is to select the best model for HUP determination. The MLRM and PCRM were developed using yearly monetary costs over 15 years of Housing Unit Major Components (HUMC) that is, cement, iron rods, aluzinc roofing sheets, coral paint, wood and sand. Multicollinearity analysis was performed to show inputs that are redundant and hence can be removed from the MLRM and PCRM development without necessarily having an effect on the modelling accuracy. With regards to TSAM, observed yearly housing unit prices over 15 years were used to determine HUP for one-bedroom and two-bedroom housing units. To overcome the nonstationarity issues, the yearly nominal housing unit prices were transformed to half-yearly real housing unit prices. The developed models were validated by using them to estimate the known HUP in the 15.5 year. From the results, the percentage absolute deviations of the estimated HUP from the known HUP for the MLRM are 1.27% and 2.02 % for one-bedroom and two-bedroom housing units respectively; for PCRM, they are 1.43% and 0.00% for one-bedroom and two-bedroom housing units respectively; and for TSAM they are all 0.00% for both one-bedroom and two- bedroom housing units. It is thus concluded that TSAM is the best model to be used to determine HUP for both one-bedroom and two-bedroom housing units respectively.


Keywords


Comparative Study, Best Model Selection, Housing Unit Price

Full Text:

PDF

References


Ayan, E. and Erkin, H. C. (2014), 'Hedonic Modeling for a Growing Housing Market: Valuation of Apartments in Complexes', International Journal of Economics and Finance, Vol. 6, No. 3, pp. 1- 12.

Boye, P., Mireku-Gyimah, D. and Okpoti, C. A. (2017), “Multiple Linear Regression Model for Estimating the Price of a Housing Unit”, Ghana Mining Journal, Vol. 17, No. 2, pp. 66 -77.

Boye, P., Mireku-Gyimah, D. and Luguterah, A. (2018), “Principal Components Regression Model for Estimating the Price of a Housing Unit”, Ghana Journal of Technology, Vol. 3, No. 1, pp. 17- 23.

Boye, P., Mireku-Gyimah, D. and Sadiq, H. (2019), “Time Series Analysis Model for Estimating the Price of a Housing Unit”, Ghana Journal of Technology, Vol. 3, No. 2, pp. 35 - 41.

Brooks, C. (2008), Introductory Econometrics for Finance, 3rd Edition, Cambridge University Press, pp. 88 - 258.

Brueggeman, W. B. and Fisher, J. D. (2001), Real Estate Finance and Investments, 14th Edition, McGraw-Hill/Irwin, pp. 193 – 203.

Chaphalkar, N. B. and Dhatunde, M. (2015), “Real Property Valuation Using Sales Comparison

Method and Multiple Regression Analysis”, International Journal of Modern Trends in

Engineering and Research, Vol. 2, No. 8, pp. 304 – 315.

Cupal, M. (2017), “Sales Comparison Approach Indicating Heterogeneity of Particular Type of Real Estate and Corresponding Valuation Accuracy”, Acta Universitatis Agriculturea Mendelianae Brunensis, Vol. 65, 977 – 985.

Efron, B. and Tibshirani, R. J. (1994), An Introduction to the Bootstrap, Chapman and Hall/ CRC, pp. 45 – 49.

Isakson, H. R. (2002), ‘The Linear Algebra of the Sales Comparison Approach’, Journal of Real Estate Research, Vol. 24, No. 2, pp. 117 – 128.

Kahr, J. and Thomsett, M.C. (2005), Real Estate Market Valuation and Analysis, John Wiley and Sons, Inc., pp. 59 – 63.

King, A. T. (1976) ‘The Demand for Housing: A Lancastrian Approach’, Southern Economic Journal, Vol. 43, No. 2, pp. 1 - 13.

Merlo, A. M. and Ortalo-Magne´, F. (2004), “Bargaining over residential real estate: evidence from England”, Journal of Urban Economics, Vol. 56, No. 2, pp. 192 – 216.

Montgomery, D. C., Jennings, C. L. and Kulahci, M. (2008), Introduction to Time Series

Analysis and Forecasting, Hoboken, N.J: Wiley-Interscience (Wiley Series in Probability and Statistics), pp. 73 - 275.


Refbacks

  • There are currently no refbacks.