Wavelets are applied to detection of the jump points of a regression function in nonlinear autoregressive model x(t) = T(x(t-1)) + epsilon t. By checking the empirical wavelet coefficients of the data,which have signi...Wavelets are applied to detection of the jump points of a regression function in nonlinear autoregressive model x(t) = T(x(t-1)) + epsilon t. By checking the empirical wavelet coefficients of the data,which have significantly large absolute values across fine scale levels, the number of the jump points and locations where the jumps occur are estimated. The jump heights are also estimated. All estimators are shown to be consistent. Wavelet method ia also applied to the threshold AR(1) model(TAR(1)). The simple estimators of the thresholds are given,which are shown to be consistent.展开更多
Wavelets are applied to a regression model with an additive stationary noise. By checking the empirical wavelet coefficients with significantly large absolute values across fine scale levels, the jump points are detec...Wavelets are applied to a regression model with an additive stationary noise. By checking the empirical wavelet coefficients with significantly large absolute values across fine scale levels, the jump points are detected first. Then the cusp points are identified by checking the wavelet coefficients with significantly large absolute values which are secondly large only to the previous wavelet coefficient across fine scale levels. All estimators are shown to be consistent.展开更多
文摘Wavelets are applied to detection of the jump points of a regression function in nonlinear autoregressive model x(t) = T(x(t-1)) + epsilon t. By checking the empirical wavelet coefficients of the data,which have significantly large absolute values across fine scale levels, the number of the jump points and locations where the jumps occur are estimated. The jump heights are also estimated. All estimators are shown to be consistent. Wavelet method ia also applied to the threshold AR(1) model(TAR(1)). The simple estimators of the thresholds are given,which are shown to be consistent.
文摘Wavelets are applied to a regression model with an additive stationary noise. By checking the empirical wavelet coefficients with significantly large absolute values across fine scale levels, the jump points are detected first. Then the cusp points are identified by checking the wavelet coefficients with significantly large absolute values which are secondly large only to the previous wavelet coefficient across fine scale levels. All estimators are shown to be consistent.
