多样本球性检验的似然比统计量的渐近分布

设Λ是检验多样本球性的修改似然比准则,本文给出了在某些接近于原假设的各择假设下Λ的非零分布的渐近展开式.     

Fitting of growth curves over time when the data are obtained from a single realization

This paper focuses on the general problem of forecasting the maximum value of a time series which by the nature of the data must approach an asymptotic value. Examples of such series include the growth of organisms, the concentration of a chemical reagent during a reaction occurring over time or the amount of a fossil fuel resource which has been discovered or produced as a function of time. The approach taken below differs from the usual models for this type of data in that it assumes that an unobserved time series is actually driving the process, and that the observed data series is a function of the unobserved process. In the case of fossil fuels the unobserved series might be a measure of the exploratory drilling, the number of production days in a given time period or even the amount of fiscal resources devoted to exploratory activities. A maximum likelihood method is developed for estimating the parameters of the process, especially the maximum S, and the covariance structure of the estimators is developed. The methodology is illustrated on an example of oil production. Finally, methods are developed for forecasting the data into the near future.     

Linear regression forecasting in the presence of ar(1) disturbances

This paper is concerned with time-series forecasting based on the linear regression model in the presence of AR(1) disturbances. The standard approach is to estimate the AR(1) parameter, ρ, and then construct forecasts assuming the estimated value is the true value. We introduce a new approach which can be viewed as a weighted average of predictions assuming different values of ρ. The weights are proportional to the marginal likelihood of ρ. A Monte Carlo experiment was conducted to compare the new method with five more conventional predictors. Its results suggest that the new approach has a distinct edge over existing procedures.     

响应变量存在缺失时非线性半参数回归模型的经验似然推断

在许多实际问题的研究中,例如临床试验、民意测验、社会问卷调查等,经常导致数据的缺失,而通常使用的统计方法都需要在样本数据完整的情况下进行.如何处理样本中的缺失数据,使得统计推断得以顺利进行,近年来越来越引起人们的广泛关注.针对响应变量存在缺失时的非线性半参数回归模型Y=f（X,β）＋g（T）＋ε,研究了参数β的经验似然推断.在一定条件下,分别基于一般借补数据和修正借补数据的情形,得到了关于参数β的对数经验似然统计量渐近服从χ2分布,并由此可以构造出关于参数β的置信域.     

Weibull分布CE模型序进试验下逐次截尾的统计分析——应力为时间的一般线性关系

针对累积损伤模型,在序进应力下给出了逐次截尾试验下两参数Weibull分布在阿伦尼斯方程下和逆幂律方程下的极大似然估计．通过Monte-Carlo模拟考察了参数估计的精度,结果表明随着样本的增大,估计的精度逐渐提高．同时,在总样本量相同的条件下,截尾样本个数较小时,估计的精度有所提高．     

A statistical method for genetic mapping of sterility genes that exhibit epistasis in remote hybridization of plants using molecular markers in an F2 population

Estimation of the position and effect of sterility genes is an important problem to be solved to understand the sterility mechanism in remote hybridization in plants.In this study,a maximum likelihood (ML) method was used for estimation of the position and effect of sterility genes that exhibit epistasis in an F 2 population using the distorted segregation of markers.The ML solutions for recombination fraction and viability were obtained via an expectation-maximization algorithm.The results of Monte Carlo simulations showed that the estimates of recombination fraction and viability were consistent with their true values.The bias and standard deviation of parameters indicated that a larger sample size,closer linkage and lower viability of sterile genes led to better estimates of the parameters involved.A subset of marker data of the F 2 population derived from a single cross between the rice japonica cultivar Nipponbare and the indica cultivar Kasalath was analyzed using this method.Eight sterility genes were identified on chromosomes 1,3,6,8 and 10,and significant epistasis was detected among four pairs of sterility genes.     

Maximum likelihood estimator for the proportional hazards model with incomplete information

Right randomly censored data with incomplete infor-mation are frequently met in practice.Although much study about right randomly censored data has been seen in the proportional hazards model,relatively little is known about the inference of regression parameters for right randomly censored data with in-complete information in such model.In particular,theoretical properties of the maximum likelihood estimator of the regression parameters have not been proven yet in that model.In this paper,we show the consistency and asymptotic normality of the maxi-mum likelihood estimator of unknown regression parameters.     

准正交空时分组码自适应设计方案与性能分析

准正交空时分组码园其牺牲部分正交性来换取全速率而无法实现全分集,在巳知信道状态信息的前提下,为最大限度降低数据符号彼此干扰,争取获得最大分集,提出两种准正交空时编码的自适应设计方案,并对其性能进行理论分析与比较,结果显示:两种自适应方案都能大大减小误码率;和增加自适应因子的方案相比,与波束形成技术相结合的自适应设计方案性能更为出色,但其增加了运算复杂度.     

估计量无偏性的证明

目前在点估计的理论和实用中 ,无偏性占据很重要的地位 ,对与同一参数的不同的点估计量 ,无偏性是对估计量最基本的要求 ,无偏估计量的证明 ,关键在于求出未知参数 θ的估计 θ的期望     

数控机床故障分析与可靠性评价技术的研究

针对传统数控机床可靠性建模时只考虑故障间隔时间而忽略故障性质的现象，提出兼顾机械故障和电气故障的混合威布尔分布模型，进而提高模型准确度.利用最大似然法来确定混合威布尔分布模型参数，用皮尔逊相关系数来确定数控机床各故障时间之间的关系.并通过K-S方法对模型进行检验， 最后确定其符合混合威布尔分布，并运用可靠性评定方法得出数控机床的平均无故障时间.