Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/153365
|
| Title: | 半參數地理加權邏輯斯迴歸在實價登錄資料分析的應用
An application of semi-parametric geographically weighted logistic regression in real estate transaction data analysis |
| Authors: | 鄭貫廷
Zheng, Guan-Ting |
| Contributors: | 陳怡如
Chen, Yi-Ju
鄭貫廷
Zheng, Guan-Ting |
| Keywords: | 實價登錄
新冠肺炎疫情
中古屋市場分析
空間異質性
半參數地理加權邏輯斯迴歸
Actual price registration
COVID-19 epidemic
Pre-owned home market analysis
Spatial heterogeneity
Semi-parametric Geographically Weighted Logistic Regression |
| Date: | 2024 |
| Issue Date: | 2024-09-04 14:56:34 (UTC+8) |
| Abstract: | 自101年8月1日起，實價登錄制度的實施使房價資訊更加透明，有助於深入分析影響房市的因素。自全球疫情爆發以來，原物料價格上漲推高了新建房屋的成本，使得價格相對穩定且地理位置優越的中古屋更受青睞。為了探討不同地區房市交易狀況與各因素之間的關係，近年來許多學者開始重視空間分析。在空間統計分析中，空間異質性 (spatial heterogeneity) 強調變數間的關係會因地區不同而有所變化；而地理加權迴歸 (Geographically Weighted Regression；GWR) 是探討此類空間異質性時備受歡迎的方法之一。然而，由於技術和軟體的限制，目前的房市分析中對於空間異質性的討論較少，特別是針對部分迴歸關係允許隨空間變動或不隨空間變動的分析更是相對缺乏。本研究認為，半參數地理加權迴歸建模技術能更準確地捕捉房市中的空間異質性。此外，儘管現有軟體已提供了半參數地理加權迴歸建模的工具，但在處理二項分佈的比例型資料時，特別是使用半參數地理加權邏輯斯迴歸模型 (Semi-parametric Geographically Weighted Logistic Regression；S-GWLR) 進行分析，仍然存在一定的侷限性，而且其在房市分析中的應用相對較少見。為了填補這一空白，本研究聚焦於中古屋成交比例資料的分析，利用新冠疫情第三級緊戒發布前後一年內新北市1032個村里的實價登錄資料，運用半參數地理加權邏輯斯迴歸技術，探討各項特徵因子對中古屋成交狀況的影響是否存在空間異質性，並比較疫情前後的變化。
本研究採用兩階段估計方法來估計半參數地理加權邏輯斯迴歸的模型參數，並透過拔靴法來估計標準誤及進行變數的空間平穩性分析。本研究利用模擬實驗進一步證實，隨著樣本量的增加，兩階段估計方法在半參數地理加權邏輯斯迴歸模型中的精確度顯著提高。在實價登錄之中古屋資料分析中，本研究將模型結果與廣義線性迴歸模型及地理加權廣義線性迴歸模型進行比較，結果顯示，半參數地理加權邏輯斯模型在表現上優於非空間廣義線性迴歸模型與地理加權廣義線性迴歸模型，顯示出其在房地產市場分析中的重要應用價值。
Since August 1, 2012, the introduction of the Actual Price Registration System has made housing price information more transparent, facilitating in-depth analysis of the real estate market. Since the outbreak of the global COVID-19 pandemic, rising raw material costs have increased the cost of newly constructed homes, making preowned home more desirable due to their relatively stable prices and advantageous locations. To explore the relationships between housing market transactions and various factors in different regions, many scholars have increasingly focused on spatial analysis in recent years. In spatial statistical analysis, spatial heterogeneity emphasizes that the relationships between variables may vary across regions, and geographically weighted regression (GWR) is a popular method for exploring such spatial heterogeneity. However, due to technical and software limitations, the discussion of spatial heterogeneity in current real estate market analysis is limited, particularly in analyses that allow some regression relationships to vary spatially while others do not.
In this study, we argue that semi-parametric geographically weighted regression modeling techniques can more effectively capture spatial heterogeneity in the housing market. In addition, while existing software provides tools for semi-parametric geographically weighted regression analysis, they have limitations when handling proportion data with a binomial distribution as the response variable, and the application of semi-parametric geographically weighted logistic regression (S-GWLR) models to real estate market analysis remains relatively rare. To address this gap, this study focuses on analyzing the proportion of transactions in preowned home using data from the Actual Price Registration System of 1032 villages in New Taipei City within one year before and after the COVID-19 pandemic. By applying S-GWLR techniques, we aim to examine the spatial heterogeneity in the regression relationships between various factors and the proportion of transactions in preowned home.
We employ a two-stage geographically weighted maximum likelihood method to estimate the parameters of the S-GWLR model. In addition, we utilize the bootstrapping method to compute the standard errors of the estimators and to conduct tests for spatial stationarity. Simulation experiments further verify that the two-stage estimation method achieves high accuracy in S-GWLR models with proportion outcomes as the sample size increases. In our empirical analysis of real estate housing data in New Taipei City, we compare the results of the S-GWLR model with those of the classical non-spatial logistic regression (LR) model and the geographically weighted generalized linear regression (GWLR) model. The findings show that the S-GWLR model outperforms both the non-spatial LR and the GWLR models, demonstrating its significant application value in real estate market analysis. |
| Reference: | Akaike, H. (1974). A new look at the statistical model identification. IEEE transactions on automatic control, 19(6):716–723.
Albuquerque, P. H. M., Medina, F. A. S., and Silva, A. R. d. (2017). Geographically weighted logistic regression applied to credit scoring models. Revista Contabilidade & Finanças, 28:93–112.
Arabameri, A., Pradhan, B., and Rezaei, K. (2019). Gully erosion zonation mapping using integrated geographically weighted regression with certainty factor and random forest models in gis. Journal of environmental management, 232:928–942.
Brunsdon, C., Fotheringham, A. S., and Charlton, M. E. (1996). Geographically weighted regression: a method for exploring spatial nonstationarity. Geographical analysis,28(4):281–298.
Burnham, K. P. and Anderson, D. R. (2004). Multimodel inference: understanding aic and bic in model selection. Sociological methods & research, 33(2):261–304.
Case, K. E. and Mayer, C. J. (1996). Housing price dynamics within a metropolitan area. Regional Science and Urban Economics, 26(3-4):387–407.
Chen, V. Y.-J., Yang, T.-C., and Matthews, S. A. (2020). Exploring heterogeneities with geographically weighted quantile regression: An enhancement based on the bootstrap approach. Geographical analysis, 52(4):642–661.
Cheung, K. S., Yiu, C. Y., and Xiong, C. (2021). Housing market in the time of pandemic:a price gradient analysis from the covid-19 epicentre in china. Journal of Risk and Financial Management, 14(3):108.
D’Lima, W. and Thibodeau, M. (2023). Health crisis and housing market effectsevidence from the us opioid epidemic. The Journal of Real Estate Finance and Economics, 67(4):735–752.
Fotheringham, A. S., Brunsdon, C., and Charlton, M. (2009). Geographically weighted regression. The Sage handbook of spatial analysis, 1:243–254.
Fotheringham, S., Brunsdon, C., and Charlton, M. (2002). Geographically weighted regression: The analysis of spatially varying relationships.
Gao, B. and He, X. (2014). The influence of demographic structure on housing price: an empirical analysis of chongqing. Modern Economy, 2014.
Hurvich, C. M. and Tsai, C.-L. (1989). Regression and time series model selection in small samples. Biometrika, 76(2):297–307.
Li, D. and Mei, C. (2018). A two-stage estimation method with bootstrap inference
for semi-parametric geographically weighted generalized linear models. International Journal of Geographical Information Science, 32(9):1860–1883.
Li, X. and Zhang, C. (2021). Did the covid-19 pandemic crisis affect housing prices evenly in the us? Sustainability, 13(21):12277.
Lin, T. C. and Hsu, S.-H. (2024). 從新冠肺炎疫情之發生分析國際住宅不動產市場. 住宅學報, 33(1):87–117.
Lu, C. and Shih, C.-L. (2014). Does population aging affect real house prices?[j]. Accessed January, 6:23–32.
Moran, P. A. (1950). Notes on continuous stochastic phenomena. Biometrika, 37(1/2):17–23.
Nakaya, T. (2015). Geographically Weighted Generalised Linear Modelling, pages 201–220.
Nakaya, T., Fotheringham, S., Charlton, M., and Brunsdon, C. (2009). Semiparametric geographically weighted generalised linear modelling in gwr 4.0.
Páez, A., Farber, S., and Wheeler, D. (2011). A simulation-based study of geographically weighted regression as a method for investigating spatially varying relationships. Environment and Planning A, 43(12):2992–3010.
Qian, X., Qiu, S., and Zhang, G. (2021). The impact of covid-19 on housing price: Evidence from china. Finance Research Letters, 43:101944.
Reichert, A. K. (1990). The impact of interest rates, income, and employment upon regional housing prices. The Journal of Real Estate Finance and Economics, 3:373–391.
Rosen, S. (1974). Hedonic prices and implicit markets: product differentiation in pure competition. Journal of political economy, 82(1):34–55.
Schwarz, G. (1978). Estimating the dimension of a model. The annals of statistics, pages 461–464.
Sisman, S. and Aydinoglu, A. C. (2022). A modelling approach with geographically
weighted regression methods for determining geographic variation and influencing factors in housing price: A case in istanbul. Land use policy, 119:106183.
Suhaida, M., Tawil, N. M., Hamzah, N., Che-Ani, A., Basri, H., and Yuzainee, M. (2011). Housing affordability: A conceptual overview for house price index. Procedia Engineering,20:346–353.
Tan, T. H. and Lee, J. H. (2018). Assessing the determinants of retirement home ownership among malaysian young-old seniors. International Journal of Housing Markets and Analysis, 11(4):687–700.
Tanaka, S. and Zabel, J. (2018). Valuing nuclear energy risk: Evidence from the impact of the fukushima crisis on us house prices. Journal of Environmental Economics and Management, 88:411–426.
Wu, B., Li, R., and Huang, B. (2014). A geographically and temporally weighted autoregressive model with application to housing prices. International Journal of Geographical Information Science, 28(5):1186–1204.
Zhao, Y. (2020). Us housing market during covid-19: aggregate and distributional evidence.
何林浩(2019). 补偿性购房动机: 持续改善的高等教育性别比与房价上涨. 财经研究, 45(1).
劉哲良、吳珮瑛、陳翰輝(2016). 不同類型土壤及地下水污染場址外溢效果之評估-那種場址對房產價值減損最大? 農業與經濟, pages 1–40.
吳森田(1994). 所得, 貨幣與房價-近二十年台北地區的觀察. 住宅學報, pages 49–65.
呂哲源、江穎慧、張金鶚(2019). 土壤液化潛勢區公布對房價之影響. Journal of City and Planning, 46(1):33–59.
彭建文、蔡怡純(2017). 人口結構變遷對房價影響分析. 經濟論文叢刊, 45(1):163–192.
施宇光(2016). 垃圾填埋场对周边住宅价值影响效应的实证分析. Shanghai Land & Resources/Shanghai Guotu Ziyuan, 37(4).
李文傑、甯方璽、黃雅祺、經濟系(2014). 集合式住宅房價泡沫形成之研究-以台中市為例. Journal of architecture, 15(2/3):155–174.
李春長、游淑滿、張維倫(2012). 公共設施, 環境品質與不動產景氣對住宅價格影響之研究─ 兼論不動產景氣之調節效果. 住宅學報, 21(1):67–87.
林忠樑、林佳慧(2014). 學校特徵與空間距離對周邊房價之影響分析-以台北市為例. 經濟論文叢刊, 42(2):215–271.
林楨家、黃至豪(2003). 台北捷運營運前後沿線房地屬性特徵價格之變化. 運輸計劃季刊, 32(4):777–800.
林祖嘉、林素菁(1993). 台灣地區環境品質與公共設施對房價與房租影響之分析.住宅學報, pages 21–45.
林祖嘉、林素菁(1994). 台灣地區住宅需求價格彈性與所得彈性之估計. 住宅學報,pages 25–48.
梁仁旭(2012). 建物價值減損之屋齡效果. 土地經濟年刊, pages 94–112.
楊宗憲、蘇倖慧(2011). 迎毗設施與鄰避設施對住宅價格影響之研究. 住宅學報, 20(2):61–80.
毛麗琴(2009). 影響房價變動因素之探討-以高雄市區爲例. 商業現代化學刊, 5(2):141–156.
江淑玲、蔡明憲、張金鶚等人(2011). 台北市中古屋價格與法拍屋拍定價格非對稱價格調整行為之研究. 管理與系統, 18(2):317–340.
沈体雁、于瀚辰、周麟、古恒宇、何泓浩(2020). 北京市二手住宅价格影响机制. 经济地理, 40(3).
洪得洋、林祖嘉(1999). 臺北市捷運系統與道路寬度對房屋價格影響之研究. 住宅學報, pages 47–67.
胡志平(2015). 住宅負擔能力之分量迴歸分析-以新竹市公寓大廈住戶為例. Journal of architecture, 16(2/3):163–182.
謝富順、張巧宜(2010). 臺灣法拍屋之拍定價格與面積關係之探究. 住宅學報, 19(2):29–57.
许正雄、杨永(1989). 法国城市地理研究方向及方法介绍. 人文地理, 4(2):15–24.
陈佛保、郝前进(2013). 环境市政设施的邻避效应研究——基于上海垃圾中转站的实证分析. 城市规划, 8:72–77.
陳建鈞、陳琨太、張秉裕(2012). 臺北市中古屋大廈模糊定價與分析. 品質學報, 19(4):349–372.
陳章瑞、宋維真(2007). Gis 調查方法於特徵價格法衡量都市綠地美質之影響與效益. 調查研究-方法與應用, pages 39–87. |
| Description: | 碩士
國立政治大學
統計學系
111354019 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0111354019 |
| Data Type: | thesis |
| Appears in Collections: | [統計學系] 學位論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| 401901.pdf | | 13350Kb | Adobe PDF | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
