本研究旨在探討利用臺灣房地產相關股票價格指數預測臺灣整體房地產價格以及各縣市房地產價格，包含了臺北市、新北市、桃園市、新竹縣市、臺中市、臺南市和高雄市。應用樣本內預測和樣本外預測的方法進行實證模型的訓練與評估。臺灣房地產相關股票價格指數是選擇與房地產相關且市值前六家的股票價格，並依各公司的市值當作權重所計算出來的股票價格指數。股票市場比起房地產市場來說，較能即時反應市場狀況，並且股票市場包含投資人對於未來房地產市場的預測資訊，因此本研究使用房地產相關股票價格指數去預測房地產價格。
在樣本內預測中可發現，大部分的縣市無論在預測短期、中期、長期後的房地產價格，房地產相關股票價格指數對於未來房地產價格呈現正相關且具有統計顯著性，即當期的房地產相關股票價格指數上升會預測未來的房地產價格會上升。在樣本外預測中可發現，可能會因縣市的不同而有不同的結果，但可以確定的是，各縣市在預測未來一、三個月時的房地產價格時，本研究利用房地產相關股票價格指數所建構的實證模型比隨機漫步模型有較佳的樣本外預測能力。此外，房地產相關股票價格指數的資訊會隨著預測時間的變長而逐漸失去效力。

This research has explored the use of Taiwan's real estate-related stock price index to predict Taiwan's overall real estate prices and real estate prices in cities, including Taiwan's Taipei City, New Taipei City, Taoyuan City, Hsinchu County City, Taichung City, Tainan City, and Kaohsiung City. The methods of in-sample prediction and out-of-sample prediction are used to train and evaluate the empirical model. The Taiwan real estate-related stock price index is a stock price index that selects the stock prices of the top six companies related to market capitalization, and recalculates the stock price index according to the market capitalization of each company. Compared with the real estate market, the stock market can respond to market conditions in a timely manner, and the stock market contains investors' future forecast information from the real estate market. Therefore, this paper uses real estate-related stock price indexes to predict real estate prices.
In the in-sample forecast, it can be found that the real estate-related stock price index is positively related to the future real estate price and has statistical significance in most cities no matter whether they are predicting short-term, medium-term, or long-term real estate prices, that is, the current real estate-related stocks an increase in the price index predicts future increases in real estate prices. In the out-of-sample forecast, it can be found that there may be different results due to different cities, but what is certain is that when predicting the real estate price in the next one or three months, this study uses the real estate-related stock price index to constructed empirical model has better predictive performance than the random walk model. In addition, the information on the real estate-related stock price index will gradually lose its effectiveness with the extension of the forecast time.

1.Baffoe-Bonnie, John (1998), “The Dynamic Impact of Macroeconomic Ag- gregates on Housing Prices and Stock of Houses: A National and Re- gional Analysis,” Journal of Real Estate Finance and Economics, 17(2), 179–197.
2.Case, Karl E., John M. Quigley, and Robert J. Shiller (2013), “Wealth Ef- fects Revisited: 1975–2012,” NBER Working Papers, No. 18667.
3.Chen, Shiu-Sheng (2014), “Forecasting Crude Oil Price Movements with Oil-Sensitive Stocks,” Economic Inquiry, 52(2), 830–844.
4.Gyourko, Joseph and Donald B. Keim (1992), “What Does the Stock Market Tell Us About Real Estate Returns?” Real Estate Economics, 20(3), 457–485.
5.Inoue, Atsushi and Lutz Kilian (2005), “In-Sample or Out-of-Sample Tests of Predictability: Which One Should We Use?” Econometric Reviews, 23(4), 371–402.
6.Lin, Tzu-Yu (2019) “Predicting House Prices with Real Estate-Related Stocks” Taiwan Economics Review,47:2, 159-182.
7.Okunev, John, Patrick Wilson, and Ralf Zurbruegg (2000), “The Causal Relationship between Real Estate and Stock Markets,” Journal of Real Estate Finance and Economics, 21(3), 251–261.
8.Quan, D.C. and S. Titman (1999), “Do Real Estate Prices and Stock Prices Move Together? An International Analysis”, Real Estate Economics, 272, 183-207.
9.Ratanapakorn, O. and Sharma, S. C. (2007), “Dynamics analysis between the US Stock Return and the Macroeconomics Variables,” Applied Financial Economics, 17(4), pp. 369-377. 
10.Sutton, Gregory D. (2002), “Explaining Changes in House Prices,” BIS Quarterly Review, September, 46–55.