시계열모형을 이용한 不動産價格 豫測에 관한 硏究

다국어 초록 (Multilingual Abstract)

The purpose of this study is to make a model to forecasting a rate of land and a housing price, using ARIMA and VAR model. On the basis of those models, I tried to forecast the fluctuations of short-term real estate price. Quarterly data during 1988. 1/4~2000. 4/4 are used for identification, estimation, diagnosis, and prediction of the model.
In analysis of the Time Series Model, the stability of variable is essential, so the unit root test was checked in Real-Estate price and macroeconomics fluctuations that are proved in the stability of time series model.
Using ARIMA model, the outcome ARIMA (2,1,1) model is applied to nationwide, ARIMA (1,1,0) model to Seoul and ARIMA (2,1,2) model to metropolis in the rate of land price forecasting model. ARIMA (2,1,2) model is also applied to the whole city in the rate of housing trade price forecasting model and in the rate of housing rental price forecasting model ARIMA (2,1,2) is applied to nationwide and Seoul. ARIMA (2,1,1,) is applied to metropolis. It was made by using ARIMA model that regional short-term forecast of Real-Estate price variable, which is based on the above outcomes.
For the second, in analysis of using VAR model, the Granger-causality test was checked between the rate of real estate price variable and macroeconomic variable to choose one that will be used in the model.
On the base of Granger-causality test, VAR model was created using macroeconomic variable and checked cointegration test. As a result, there is no cointegration relationship in the land price forecasting model. In the housing trade price forecasting model and in the rental price forecasting model has one cointegration relationship in whole city and Seoul otherwise in metropolis estimate model has nothing.
Using the entire examined outcomes, VAR model is applied to estimate each regional the rate of land price forecasting model. For Seoul and the whole city's rate of housing trade price and the rental price forecasting model is estimated by VECM model and VAR model to metropolis.
The advantages of using VAR model are in that it is simple relative to the structural econometric model, it can reflect the relationships among other affecting variables relative to ARIMA model.
In advance to establish VAR model, land and housing market analysis is accomplished to promote understanding of the relationships among concerned variables and to select proper variables to be used in the VAR model.
According to the forecast result rate of real estate price in the VAR model, the rate of land price in 2002 is fluctuated to be -0.22% to nationwide, 0.04% to Seoul and -0.45% to metropolis. The next, housing trade price is fluctuated to be 0.91% to nationwide, 1.28% to Seoul and 0.37% to metropolis. The last, housing rental price is fluctuated to be 3.74% to nationwide, 5.43% to Seoul and 3.060.37% to metropolis. housing trade price is fluctuated to be 0.91% to nationwide, 1.28% to Seoul and 0.37% to metropolis.
1.

목차 (Table of Contents)

• 목차
• 第1章 序論 = 1
• 第1節 硏究의 背景 및 目的 = 1
• 第2節 硏究의 範圍 및 方法 = 2
• 第2章 부동산가격 동향 = 4
• 弟1節 분석자료의 선정 = 4
• 第2節 지가동향과 거시경제와의 관계 = 6
• 1. 지가동향 = 6
• 2. 지가와 거시경제와의 관계 = 9
• 弟3節 주택가격 동향과 거시경제와의 관계 = 14
• 1. 주택가격 동향 = 14
• 2. 주택가격과 거시경제와의 관계 = 18
• 弟4節 선행연구 검토 = 24
• 第3章 시계열모형에 관한 이론적 고찰 = 26
• 第1節 시계열의 안정성 및 단위근 검정 = 26
• 1. 시계열의 안정성 = 26
• 2. 자기상관함수와 편자기상관함수 = 28
• 3. 단위근검정(unit root tests) = 30
• 第2節 ARIMA모형 = 32
• 1. 확률적 시계열모형 = 32
• 2. Box-Jenkins방법론 = 35
• 第3節 벡터자기회귀모형 = 39
• 第4節 공적분과 오차수정모형 = 41
• 1. 허구적 회귀와 공적분의 개념 = 41
• 2. 오차수정모형(error correction model) = 43
• 第4章 ARIIMA모형을 이용한 예측 = 45
• 第1節 지가의 예측 = 45
• 1. 지가변동률의 안정성 검정 = 45
• 2. 지가변동률 예측모형의 설정 및 추정 = 46
• 3. 지가의 예측 = 49
• 第2節 주택매매가격의 예측 = 51
• 1. 주택매매가격변동률의 안정성 검정 = 51
• 2. 주택매매가격변동률 예측모형의 설정 및 추정 = 52
• 3. 주택매매가격의 예측 = 55
• 第3節 주택전세가격의 예측 = 57
• 1. 주택전세가격변동률의 안정성 검정 = 57
• 2. 주택전세가격변동률 예측모형의 설정 및 추정 = 58
• 3. 주택전세가격의 예측 = 61
• 第5章 VAR모형을 이용한 예측 = 63
• 第1節 거시경제변수의 안정성 검정 = 63
• 第2節 그랜저 인과관계 검정 = 64
• 1. 지가와 거시경제변수간의 그랜저 인과관계검정 = 66
• 2. 주택매매가격과 거시경제변수간의 그랜저 인과관계검정 = 67
• 3. 주택전세가격과 거시경제변수간의 그랜저 인과관계검정 = 69
• 第3節 지가의 예측 = 71
• 1. 지가변동률 예측모형의 설정 및 추정 = 71
• 2. 지가의 예측 = 74
• 第4節 주택매매가격의 예측 = 76
• 1. 주택매매가격예측모형의 설정 및 추정 = 76
• 2. 주택매매가격의 예측 = 80
• 第5節 주택전세가격의 예측 = 82
• 1. 주택전세가격예측모형의 설정 및 추정 = 82
• 2. 주택전세가격의 예측 = 86
• 第6章 要約 및 結論 = 88
• <참고문헌> = 95
• ABSTRACT = 97