公園與社區居民生活具密切關係,多數居民在選擇居住區位時,外部性影響因素常是重要考量依據,然相關研究中有關公園對不動產交易價格影響實證探討並不多,本研究爰以民國100年原高雄市行政區之不動產交易價格為實證資料,從空間層面探討原高雄市不動產交易價格之空間分佈以及聚集現象,以了解原高雄市各類型公園對不動產交易價格影響之變化情形。研究結果顯示,原高雄市不動產交易價格具明顯空間聚集趨勢、都市公園對不動產交易價格影響較其它類型公園影響顯著,復比較特徵價格模型與空間自我相關模型校估結果發現,空間自我相關模型對特徵價格模型解釋能力之改善程度明顯提高,其中又以空間誤差模型校估結果較佳。
This study explores the impact of different types of parks on the transaction prices of real estate in Kaohsiung city during 2011. GIS data of geospatial information, and real estate transactions were subpoenaed for spatial statistics analysis, in which the spatial regression models were included to correct the bias caused by spatial autocorrelation. The empirical results showed that the transaction prices of real estate exhibited a greater spatial correlation. The impact of the neighbor park and the city park on the transaction prices of real estate were much more significant than other types of parks. Besides, comparing the estimation results of the hedonic regression model with the spatial autocorrelation models’, it indicated that the spatial error regression model was much better in evaluating the impact of different types of parks on the transaction prices of real estate.