01 May 2006, Volume 22 Issue 2
    

  • Select all
    |
    论文
  • FU Juesheng, ZHU Hongyin, WANG Renguan
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 113-119.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    In this paper, it is discussed the decomposition of signal-to--noise ratios
    with application to the robust design. The conception of PerMIA, which gives
    the connection between the G.Taguchi's signal-to-noise ratios and his social
    average quadratic loss, is quoted. As an example, the problem in the CMCM-97
    is analyzed using the approach and it can be concluded that this approach is
    more convenient in optimization procedure to parameter design.
  • WANG Wenxin, LI Xiaohu
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 120-126.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    Reversed preservation properties of the right spread order, the total time on
    test transform order, the increasing concave order and the increasing convex
    order under the taking of random maxima and minima are investigated respectively. As application, reversed preservation properties of some related aging conceptions under the taking of random maxima and minima are developed as well.
  • WANG Meichen, YE Cinan, XU Dongyuan
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 127-136.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    Consider a dependent bivariate distribution whose reliability function is $$
    \ol{F}(x_1,x_2)=\exp\{-[(x_1^{1/\alpha}/\theta_1)^{1/\delta}
    +(x_2^{1/\alpha}/\theta_2)^{1/\delta}]^{\delta}\},
    \;\;\;x_i>0,\,\alpha>0,\,1\geq\delta>0,\,\theta_i>0\;(i=1,2).
    $$Two kinds of stress-strength model are discussed respectively. Moment-type
    estimators of structural reliability for those models are proposed and their
    asymptotic properties are discussed. At last, a simulation result is given.
  • ZHU Liping, LU Yiqiang; MAO Shisong
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 137-150.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    Mixed exponentially distribution failure time distributions play an important role in life time data analysis. But we may encounter enormous difficulties when we try to estimate the model by traditional methods such as maximize likelihood (ML) estimation and moment estimation. In this paper, we employ the EM algorithm to obtain the ML estimation for the mixed exponential model under the normal stress life time test with full data or censored samples. The iteration formula are given in the paper. Simulations are also made to evidence the performance of estimation.
  • CHEN Yiqing; DONG Xiaoju; XIE Xiangsheng
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 151-158.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    In this paper, we investigate the ruin probability of a discrete-time risk model, in which the surplus of an insurance business is currently investedinto a risky asset. Using a purely probabilistic treatment, we establishexplicit asymptotic relations for the infinite-time ruin probabilities,hence we extend a recent result of Tang and Tsitsiashvili (2003) to the infinite-time case.
  • ZHAO Xiaobing
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 159-172.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    We consider a class of semi-parametric transformation models, under which an
    unknown transformation of the survival time is linear related to the covariates
    with various error distributions, which are parametrically specified with unknown parameters. Estimators of the coefficients of covariates are obtained from linear least squares procedures and the Class-K method with censored observations. We show that the estimators are consistent and asymptotically normal. This transformation model, coupled with proposed inference procedures, provides many alternatives to the Cox models and survival analysis.
  • XIE Fengchang; WEI Bocheng
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 173-183.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    For the data from multivariate $t$ distribution, it is hard to do influence analysis
    based on its probability density function. But it can be considered as a particular
    Gaussian mixture by introducing the weight from the Gamma distribution. Based on this fact, we treat the weight as the missing data and develop the local influence analysis for the data from multivariate $t$ distribution based on the conditional expectation of the complete-data log-likelihood function in the EM algorithm. The local influence based on the case-weights perturbation is discussed in detail and two numerical examples are given to illustrate our results.
  • SHU Huisheng;ZHAO Guoliang
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 184-194.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    In this paper, we investigate the robust stochastic stability for a class of continuous time-varying delay uncertain systems with Markovian switching. The
    Markovian switching considered here forms a continuous-time discrete-time
    homogeneous Markov process. In terms of stochastic Lyapunov function method
    and linear matrix inequality, sufficient criterion for testing the robust stochastic stability of systems are proposed respectively. Finally, a numerical example is given to illustrate the effectiveness of the proposed method.
  • WU Yaohua,GONG Jun
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 195-200.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    BRPA estimator, proposed in Changchien (1990), has certain merits over the estimators derived through the estimation of the regression function. Some of the properties of the BRPA estimator have been studied in Chen, Huang and Huang (1996), Bai and Huang (1999), Wu and Wang (2000) and Bai, Chen and Wu (2003). In this article, we give the convergence rate of the BRPA estimator of the multivariate regression function under some mild conditions and popularize the result of Bai, Chen and Wu (2003).
  • CHEN Pingyan,DAI Yonglong
    CHINESE JOURNAL OF APPLIED PROBABILITY AND STATIST. 2006, 22(2): 201-207.
    Abstract ( ) Download PDF ( ) Knowledge map Save
    In this paper, we obtain the almost sure bound of normal sum of $B$-valued
    weakly dependent random variables under the assumption that Banach space $B$ is $p$-smoothable ($1<p\leq2$). As its application, we characterize
    $p$-smoothness of Banach space through the strong law of large numbers of
    $B$-valued $y$-mixing random variables, and obtain some results on the strong
    law of large numbers for $B$-valued dependent random variables without
    assumption on rate of tending to zero of $\varphi$ and $\psi$-mixing parameters
    $\varphi_n$ and $\psi_n$ but under the assumption that $\inf\limits_{n\geq1}
    \varphi_n=0$ or $\inf\limits_{n\geq1}\psi_n=0$ respectively.