本研究以房貸負擔率作為門檻變數,探討可支配所得及消費物價指數與房貸負擔率影響是否存在結構性的變化。 本研究採用Enders and Siklos(2001)利用門檻自我迴歸模型(Threshold Autoregressive Model, TAR),找出迴歸式中之最小平方法估計值,接著利用Enders and Siklos(2001)提出動差門檻自我迴歸(Momentum- Threshold Autoregressive Model, M-TAR)進行門檻共整合檢定。實證結果發現在非線性ADF NP、PP與KPSS單根檢定法中,檢定可支配所得及消費物價指數與房貸負擔率皆為I(1)時間數列資料。在門檻共整合檢定部份,發現可支配所得及消費物價指數與房貸負擔率皆存在長期的非對稱門檻共整合關係。最後,研究中從門檻誤差修正模型發現,可支配所得及消費物價指數與房貸負擔率短期皆呈現不顯著,皆無短期因果關係之存在,而可支配所得與房貸負擔率研究中的可支配所得與房貸負擔率不具長期因果關係,但消費物價指數與房貸負擔率之間的長期存在著均衡的非對稱共整合關係。
This study takes the mortgage burden rate as the threshold variable to explore the disposable income of each household in Taiwan's six municipality directly under the central government, and whether there is structural change in the impact of the mortgage rate on the six municipality directly under the central government. In this study, Enders and Siklos (2001) used the Threshold Autoregressive Model (TAR) to find the least squares estimates in the regression, and then proposed the use of Enders and Siklos (2001) to measure the threshold threshold self-regression (Momentum - Threshold Autoregressive Model, M-TAR). The empirical results show that the non-linear ADF、NP、PP and KPSS single test, test Disposable Income and Consumer Price Index and Mortgage Burden are all I (1) time series data. The results of TECM Granger-Causality tests show a short-run causal relationship exists between Disposable Income and Consumer Price Index and Mortgage Burden. And no short-run causal relationship exists between Disposable Income and Consumer Price Index and Mortgage Burden. However, there is no long-term causal relationship between Disposable Income and Mortgage Burden, and there is a long-term equilibrium relationship between the Consumer Price Index and Mortgage Burden.