误差不独立的变量含误差模型的强相合性

研究了一类误差不独立的变量含误差模型,其中,x∈Rp为非随机解释变量,误差εi(i=1,2…,n)不独立,通过应用最大似然法和特征向量法得出了未知参数估计,在较弱的条件下,证明了估计的强相合性.     

一类半参数模型的参数估计及收敛速度

对于一类半参数回归模型推广了近邻权与核权，使之统一。并证得了在该推广权下，非参数估计仍具有良好的性质。     

一类半参数回归模型的经验似然

考虑一类半参数回归模型yi=xi′β+g(xi)+ei,1≤i≤n,其中xi=(xi1,xi2,…,xik)′是固定设计点列,β=(β1,β2,…,βk)′是未知待估参数,g(.)是未知函数,ei是随机误差,且E(ei)=0,E(ei2)=σ2∞.首先假设β已知,用非参数权函数方法估计非参数部分g,然后应用经验似然方法构造似然函数,证明了经验对数似然比统计量渐近服从卡方分布.结果可用于构造半参数回归模型中参数向量的置信区域.     

随机删失下半参数回归模型中估计的渐近性质

考虑半参数回归模型Yi=xiβ g(ti) iσiε,i=1,2,…,n,其中2iσ=f(ui).当Yi因受某种随机干扰而被随机右删失时,就删失分布未知的情形,利用所获得的删失数据定义了β与g(t)的估计^βn和^gn(t),在适当的条件下,证明了^nβ的渐近正态性,同时得到了^gn(t)的最优收敛速度.     

一类半参数回归模型的渐近正态性

半参数回归模型（包括部分线性回归模型）是当今统计学界研究的热点课题之一,研究了一类基于网点观测的部分线性回归模型,利用最小二乘法给出了未知参数和误差方差的估计,在一般条件下,证明了估计量的渐近正态性。     

非齐次线性模型M估计的强相合性

研究非齐次线性模型M估计的强相合性.通过分析模型的统计性质,在比相关文献更弱的条件下,证明了非齐次线性模型M估计强相合的充分条件是δn=max1≤i≤n(xi-n)′Tn-1(xi-n)=O(n-δ),其中0<δ<1,并证明若要δ=1时结论依然成立须加强条件.本文结果比文献中的相应结果有所改进,文献结果可由本文结果导出.     

误差为AANA序列的部分线性模型的弱相合性

研究误差为渐近几乎负相依序列的部分线性模型的性质.利用最小二乘法和非参数加权的估计方法,得到参数、非参数和误差方差的估计,并在合适的条件下得到这些估计量的弱相合性,推广了误差为负相依序列的部分线性模型的相关结论.     

随机右删失部分线性模型中小波估计的强相合性

研究随机右删失部分线性模型中回归参数β和回归函数g（t）的估计问题.分别在删失分布函数已知和未知的情形下,基于变换后的观测数据构造了β和g（t）的小波估计,在适当的条件下,证明了它们均具有强相合性.     

缺失数据下局部估计的弱相合性和渐近正态性

在缺失响应变量的不完全数据下,对非参数回归模型进行研究．利用局部线性回归方法,给出了回归函数m（x）的估计,并给出了条件偏差和条件渐近方差,证明了缺失数据下局部估计具有渐近正态性和弱相舍性．     

基于图像阶调与人眼视觉模型的彩色误差扩散网目调方法

在彩色误差扩散网目调处理过程中,各色通道不同的误差滤波器设计将直接影响彩色网目调图像的质量.本文对基于阶调的误差扩散方法以及人眼视觉特性进行了分析研究,应用亮度和色度人眼视觉模型对误差扩散过程中的滤波器系数和阈值进行优化,实现了基于图像阶调与人眼视觉模型的彩色误差扩散网目调方法.实验结果表明,该方法能够有效地减少彩色网目调图像的人工纹理,并显著提高再现彩色图像的色彩还原精度.     

高浓度锥形磨浆机力学模型

分析了高浓度锥形磨浆机磨浆区内的受力情况,提出了一种相应的力学模型。由于在高浓磨浆过程中,纸浆纤维除了受到磨盘作用力以外,还受到纤维间的作用力,故该模型由两大部分组成。其中,由于磨盘采用平面与锥面相结合的方式,为简化模型,在分析磨盘对纤维的作用力时,将平磨区和锥磨区分别考虑。     

线性模型的岭型广义逆估计

从LS估计出发 ,基于设计阵的奇异值分解式 ,应用岭估计方法 ,构造了回归系数的一个新的有偏估计———岭型广义逆估计 .计算结果表明 ,在设计阵呈病态时 ,岭型广义逆估计确能明显改善LS估计 .     

Analysis of age-specific predicted transmitting abilities for final scores in Holsteins with a random regression model

Conformation final scores obtained by the Holstein Association were used in this study. Five subsets were sampled from the original complete data, which contained about 7 million records, and (co)variance components for additive genetic, permanent environmental, and residual effects were estimated with a multiple-trait (MT) model at different ages of cows and with a random regression model. Transmitting abilities were predicted with the random-regression (RR) model and with the repeatability model for the national evaluation, using the entire data set. The RR model included fixed and random regressions on age at classification for additive genetic and permanent environmental effects. Additive genetic and residual variances estimated with the MT model increased with aging. Genetic correlations between age groups decreased with their distance. Heritability and repeatability estimates with the RR model were 0.27 and 0.88 on average, increasing with cow's age. Correlations between transmitting abilities predicted with the RR model at various ages and with the repeatability model were in the range of 0.89 to 0.99. In the 1980s, predicted transmitting abilities (PTA) of sires increased with their daughters' age, but in 1991 and 1995, the PTA decreased. In general, sires whose daughters were evaluated at mature ages tended to have higher PTA. For sires and cows, genetic trends estimated from the repeatability model and from the RR model were similar. The low genetic trend of cows at 60 mo for recent years was due to many grade cows that had only single records and little pedigree information.     

Genetic parameters for tunisian holsteins using a test-day random regression model

Genetic parameters of milk, fat, and protein yields were estimated in the first 3 lactations for registered Tunisian Holsteins. Data included 140,187; 97,404; and 62,221 test-day production records collected on 22,538; 15,257; and 9,722 first-, second-, and third-parity cows, respectively. Records were of cows calving from 1992 to 2004 in 96 herds. (Co)variance components were estimated by Bayesian methods and a 3-trait-3-lactation random regression model. Gibbs sampling was used to obtain posterior distributions. The model included herd × test date, age × season of calving × stage of lactation [classes of 25 days in milk (DIM)], production sector × stage of lactation (classes of 5 DIM) as fixed effects, and random regression coefficients for additive genetic, permanent environmental, and herd-year of calving effects, which were defined as modified constant, linear, and quadratic Legendre coefficients. Heritability estimates for 305-d milk, fat and protein yields were moderate (0.12 to 0.18) and in the same range of parameters estimated in management systems with low to medium production levels. Heritabilities of test-day milk and protein yields for selected DIM were higher in the middle than at the beginning or the end of lactation. Inversely, heritabilities of fat yield were high at the peripheries of lactation. Genetic correlations among 305-d yield traits ranged from 0.50 to 0.86. The largest genetic correlation was observed between the first and second lactation, potentially due to the limited expression of genetic potential of superior cows in later lactations. Results suggested a lack of adaptation under the local management and climatic conditions. Results should be useful to implement a BLUP evaluation for the Tunisian cow population; however, results also indicated that further research focused on data quality might be needed.     

Genetic parameters for a multiple-trait multiple-lactation random regression test-day model in Italian Holsteins

The objectives of this study were to estimate variance components for test-day milk, fat, and protein yields and average daily SCS in 3 subsets of Italian Holsteins using a multiple-trait, multiple-lactation random regression test-day animal model and to determine whether a genetic heterogeneous variance adjustment was necessary. Data were test-day yields of milk, fat, and protein and SCS (on a log₂ scale) from the first 3 lactations of Italian Holsteins collected from 1992 to 2002. The 3 subsets of data included 1) a random sample of Holsteins from all herds in Italy, 2) a random sample of Holsteins from herds using a minimum of 75% foreign sires, and 3) a random sample of Holsteins from herds using a maximum of 25% foreign sires. Estimations of variances and covariances for this model were achieved by Bayesian methods using the Gibbs sampler. Estimated 305-d genetic, permanent environmental, and residual variance was higher in herds using a minimum of 75% foreign sires compared with herds using a maximum of 25% foreign sires. Estimated average daily heritability of milk, fat, and protein yields did not differ among subsets. Heritability of SCS in the first lactation differed slightly among subsets and was estimated to be the highest in herds with a maximum of 25% foreign sire use (0.19 ± 0.01). Genetic correlations across lactations for milk, fat, and protein yields were similar among subsets. Genetic correlations across lactations for SCS were 0.03 to 0.08 higher in herds using a minimum of 75% or a maximum of 25% foreign sires, compared with herds randomly sampled from the entire population. Results indicate that adjustment for heterogeneous variance at the genetic level based on the percentage of foreign sire use should not be necessary with a multiple-trait random regression test-day animal model in Italy.     

造纸生化污泥、芬顿污泥与低浓浆渣混合脱水的工艺与设备

针对生化污泥、芬顿污泥难脱水的问题,通过与低浓浆渣按一定比例混合后,采用螺旋挤压脱水设备处理,可以获得固含量50%以上的出泥干度。且该污泥含有较高热值,进入电厂锅炉焚烧可解决造纸污泥的综合利用问题。本文结合螺旋压榨脱水系统的实际应用经验,对生化污泥、芬顿污泥与浆渣混合后的脱水工艺的运行方案、设备配置和运行控制等进行了详细分析与探讨。     

一类带有交叉扩散的捕食-食饵模型的全局分歧

研究了一类带有交叉扩散项的捕食-食饵模型的Dirichlet 问题正解的存在性。利用极大值原理得到了正解的先验估计,借助Crandall-Rabinowitz 分歧理论,得到了局部分歧正解的存在性,并将局部分歧延拓为全局分歧,从而得到正解存在的充分条件。最终结果表明,在一定条件下捕食者与食饵可以共存。