Locational impact on residential property assessment in the City of Edmonton
Loading...
Issue Date
2020-08
Editor
Authors
Jacob, Amita
License
Subject
Abstract
This study compares 8 hedonic house price models for single family properties in Edmonton, Canada. The study starts with the widely used Ordinary least squares regression model as a benchmark followed by the application of spatial econometric and statistical models.
The exploratory and auxiliary analyses included 177,545 single-family housing units distributed across the 12 electoral ward boundaries within Edmonton. The study aims to arrive at the best performing model given the selected variables and understand how those variables or factors impact the home assessment values in Edmonton.
The R2 and AIC serve as metrics to compare the models and assess the goodness of fit. Results indicate that the spatial lag model with 5 factors is the best performing model.