Page 127 - Contributed Paper Session (CPS) - Volume 1

CPS1198 Firano Z. et al.
Thus, the index of repeated sales over a period requires observing the goods
that are trading during a given time interval. This market-based approach is
sound in the sense that it captures all transactions made on the asset in
question. However, it neglects the economic aspects and the factors that favor
the realization of the sale and the purchase.
To this end, we propose in this paper a new approach to the development
of a real estate index. This is indeed the hedonic approach whose design is
more or less based on the theoretical training of real estate prices.
Hedonistic price models have been used in housing studies since
(Lancaster, 1966) and Rosen (1974) to explore the determinants of housing
prices. In the last three decades, this form of modelling has been used to
evaluate the value of real estate worldwide. In this design, the choice of
housing confers not only the consumption of the property and the structural
characteristics of the dwelling, but the consumption of all the characteristics
of the property's location such as proximity to environmental benefits and
utilities.
This paper aims to model the determinants of real estate prices in Morocco
based on the characteristics of goods sold and bought on the Moroccan
market. In addition, the paper also proposes to develop the hedonic index by
referring to an approach borrowed from stochastic finance where real estate
prices are supposed to follow a Brownian geometric movement.
Of those, this article will be structured as follows: in a first, we will present
an empirical literature review of work on the issue. Then, a presentation of the
methodology and the data used, will allow understanding the nature of the
variables retained and the technique used for the development of the new
index. Finally, the last part of the article will focus on the presentation of the
results and possible interpretations of the new index.

2. Literature review
Early work applying the hedonic modelling approach to real estate prices
started in the early 1920s, despite the fact that there is no consensus as to the
actual date of their introduction. For example, Colwell and Dilmore (1999)
reported that Haas' work in 1922 is the pioneering study to evaluate farmland
in Minnesota (USA). Similarly, Bruce and Sundell (1977) have argued that this
technique was used in real estate valuation research in 1924. In addition,
Wallace (1926) adopted the HPM technique in US cropland. Ridker and
Henning (1967) used HPM for the evaluation of air quality and air quality on
residential property values.
Other studies have tried to explain the time required to sell a house and
the reasons for this decision. Indeed, two approaches have been adopted
namely: duration models and linear regression models. The use of duration
models is justified by the significance of time in determining selling prices in

116 | I S I W S C 2 0 1 9