In this paper, we give a detailed description of the local behavior of theLipschitz-1/2 modulus for cumulative hazard process and PL-process when the data are subject to lefttruncation and right censored observations....In this paper, we give a detailed description of the local behavior of theLipschitz-1/2 modulus for cumulative hazard process and PL-process when the data are subject to lefttruncation and right censored observations. We establish laws of the iterated logarithm of theLipschitz-1/2 modulus of PL-process and cumulative hazard process. These results for the PL-processare sharper than other results found in the literature, which can be used to establish theasymptotic properties of many statistics.展开更多
In this paper we obtain exact rates of uniform convergence for oscillation moduli and Lipschitz-1/2 moduli of PL-process and cumulative hazard process when the data are subject to left truncation and right censorship....In this paper we obtain exact rates of uniform convergence for oscillation moduli and Lipschitz-1/2 moduli of PL-process and cumulative hazard process when the data are subject to left truncation and right censorship. Based on these results, the exact rates of uniform convergence for various types of density and hazard function estimators are derived.展开更多
Based on the analysis of wavelet transform and PLS,a new type of neural network:wavelet function based neural network with nonlinear PLS has been proposed and applied to dynamic process monitoring.According to the com...Based on the analysis of wavelet transform and PLS,a new type of neural network:wavelet function based neural network with nonlinear PLS has been proposed and applied to dynamic process monitoring.According to the complicated properties of the noise in the real process,a filter algorithm using orthonomal discrete wavelet transform has been proposed.The theoretical analysis and application results have shown that the algorithms are feasible and effective.展开更多
文摘In this paper, we give a detailed description of the local behavior of theLipschitz-1/2 modulus for cumulative hazard process and PL-process when the data are subject to lefttruncation and right censored observations. We establish laws of the iterated logarithm of theLipschitz-1/2 modulus of PL-process and cumulative hazard process. These results for the PL-processare sharper than other results found in the literature, which can be used to establish theasymptotic properties of many statistics.
基金Research supported by the Postdoctoral Programme Foundationthe National Natural Science Foundation of China
文摘In this paper we obtain exact rates of uniform convergence for oscillation moduli and Lipschitz-1/2 moduli of PL-process and cumulative hazard process when the data are subject to left truncation and right censorship. Based on these results, the exact rates of uniform convergence for various types of density and hazard function estimators are derived.
文摘Based on the analysis of wavelet transform and PLS,a new type of neural network:wavelet function based neural network with nonlinear PLS has been proposed and applied to dynamic process monitoring.According to the complicated properties of the noise in the real process,a filter algorithm using orthonomal discrete wavelet transform has been proposed.The theoretical analysis and application results have shown that the algorithms are feasible and effective.
