본문 바로가기
  • Home

A Study on the Estimation of Seoul Apartment Price Index Using Spatiotemporal Autoregression Model

Park, Heonsoo 1 Kim, Junghoon 2

1중앙대학교
2영남대학교

Accredited

ABSTRACT

The estimation of the housing price index has mainly been studied in a traditional way of the regression analysis. When spatial and temporal effects are disregarded in the model, however, those effects lead to distort and mislead parameter estimates and statistical inference. This article addresses spatio-temporal autocorrelation in apartment price using OLS, temporal autoregressive model, spatial autoregressive model and spatio-temporal autoregressive model in 225 apartment complexes. Using 8,822 observations on apartment price in the southern Seoul from 1994 to 2003, this article demonstrates the substantial benefits obtained by modeling the spatial as well as the temporal dependence of the data. Specifically, the spatiotemporal autoregression with thirteen variables reduced root mean squares error (RMSE) by 71.6% relative to an indicator-based model with twenty-nine variables.

Citation status

* References for papers published after 2023 are currently being built.