Adaptive Random Effects/Coefficients Modeling

Adaptive fractional polynomial modeling of general correlated outcomes is formulated to address nonlinearity in means, variances/dispersions, and correlations. Means and variances/dispersions are modeled using generalized linear models in fixed effects/coefficients. Correlations are modeled using random effects/coefficients. Nonlinearity is addressed using power transforms of primary (untransformed) predictors. Parameter estimation is based on extended linear mixed modeling generalizing both generalized estimating equations and linear mixed modeling. Models are evaluated using likelihood cross-validation (LCV) scores and are generated adaptively using a heuristic search controlled by LCV scores. Cases covered include linear, Poisson, logistic, exponential, and discrete regression of correlated continuous, count/rate, dichotomous, positive continuous, and discrete numeric outcomes treated as normally, Poisson, Bernoulli, exponentially, and discrete numerically distributed, respectively. Example analyses are also generated for these five cases to compare adaptive random effects/coefficients modeling of correlated outcomes to previously developed adaptive modeling based on directly specified covariance structures. Adaptive random effects/coefficients modeling substantially outperforms direct covariance modeling in the linear, exponential, and discrete regression example analyses. It generates equivalent results in the logistic regression example analyses and it is substantially outperformed in the Poisson regression case. Random effects/coefficients modeling of correlated outcomes can provide substantial improvements in model selection compared to directly specified covariance modeling. However, directly specified covariance modeling can generate competitive or substantially better results in some cases while usually requiring less computation time.

ROBUST ESTIMATION IN PARTIAL LINEAR MIXED MODEL FOR LONGITUDINAL DATA

In this article, robust generalized estimating equation for the analysis of partial linear mixed model for longitudinal data is used. The authors approximate the nonparametric function by a regression spline. Under some regular conditions, the asymptotic properties of the estimators are obtained. To avoid the computation of high-dimensional integral, a robust Monte Carlo Newton-Raphson algorithm is used. Some simulations are carried out to study the performance of the proposed robust estimators. In addition, the authors also study the robustness and the efficiency of the proposed estimators by simulation. Finally, two real longitudinal data sets are analyzed.

Nonparametric Estimation in Linear Mixed Models with Uncorrelated Homoscedastic Errors

Today, Linear Mixed Models (LMMs) are fitted, mostly, by assuming that random effects and errors have Gaussian distributions, therefore using Maximum Likelihood (ML) or REML estimation. However, for many data sets, that double assumption is unlikely to hold, particularly for the random effects, a crucial component in which assessment of magnitude is key in such modeling. Alternative fitting methods not relying on that assumption (as ANOVA ones and Rao’s MINQUE) apply, quite often, only to the very constrained class of variance components models. In this paper, a new computationally feasible estimation methodology is designed, first for the widely used class of 2-level (or longitudinal) LMMs with only assumption (beyond the usual basic ones) that residual errors are uncorrelated and homoscedastic, with no distributional assumption imposed on the random effects. A major asset of this new approach is that it yields nonnegative variance estimates and covariance matrices estimates which are symmetric and, at least, positive semi-definite. Furthermore, it is shown that when the LMM is, indeed, Gaussian, this new methodology differs from ML just through a slight variation in the denominator of the residual variance estimate. The new methodology actually generalizes to LMMs a well known nonparametric fitting procedure for standard Linear Models. Finally, the methodology is also extended to ANOVA LMMs, generalizing an old method by Henderson for ML estimation in such models under normality.

Efficient Shrinkage Estimation about the Partially Linear Varying Coefficient Model with Random Effect for Longitudinal Data

In this paper, an efficient shrinkage estimation procedure for the partially linear varying coefficient model (PLVC) with random effect is considered. By selecting the significant variable and estimating the nonzero coefficient, the model structure specification is accomplished by introducing a novel penalized estimating equation. Under some mild conditions, the asymptotic properties for the proposed model selection and estimation results, such as the sparsity and oracle property, are established. Some numerical simulation studies and a real data analysis are presented to examine the finite sample performance of the procedure.

双反应变量重复测量资料分析及MIXED过程实现

目的探讨双反应变量重复测量资料的分析原理与方法及SAS软件PROCMIXED过程的应用。方法结合双反应变量重复测量数据的特点,采用SAS软件的MIXED过程对其进行分析,建立线性混合效应模型。结果该模型不仅考虑了每个变量多次重复测量结果之间的相关性,也考虑了两个变量之间的相关性,同时还引入固定效应和随机效应,结合数据特征分析,结果更为可信。结论对双反应变量非独立重复测量资料,可以把数据之间的相关性分解为重复测量间相关性和变量间相关性两部分,采用MIXED过程不仅可对其相关性做出明晰深入的分析,且可保证数据分析结果解释更符合实际。

基于SAS NLMIXED的广义线性混合效应模型在发病率数据Meta分析中的应用

目的:介绍利用SAS软件中的PROC NLMIXED过程步实现发病率数据的META分析方法。方法:基于广义线性混合效应模型(GLMM)的二项式-正态模型(BN)和泊松-正态模型(PNM)等,可方便地实现发病率数据的随机效应Meta分析,尤其当Meta分析纳入含0事件研究时。以Schutz等发表的血管内皮生长因子受体酪氨酸激酶抑制剂治疗的癌症患者发生致命不良事件风险的系统评价作为实例数据,利用SAS软件实现发病率数据的META分析,并提供编程代码。结果:对于含0事件研究,使用PNM模型进行Meta分析,无需进行连续校正法。删除0事件研究对于PNM模型影响较大。与标准正态模型相比,PNM和BNM模型给出的效应值更高,而P值则更小,具有更好的灵敏性。结论:基于广义线性混合效应模型,利用SAS的PROCNLMIXED实现发病率数据Meta分析是优选的方法。

Effects of breeding success,age and sex on breeding dispersal of a reintroduced population of the Crested Ibis(Nipponia nippon)in Ningshan County,China

Background: Breeding dispersal is an important ecological process that affects species' population dynamics and colonization of new suitable areas. Knowledge of the causes and consequences of breeding dispersal is fundamental to our understanding of avian ecology and evolution. Although breeding success for a wild and reintroduced population of the Crested Ibis(Nipponia nippon) has been reported, the relationships between individuals' breeding dispersal and their breeding success, age and sex remain unclear.Methods: Ibises' breeding dispersal distance, which is the distance moved by adults between sites of reproduction, was estimated based on the observations of consecutive breeding sites of marked ibis individuals. From observational and capture-recapture data(n as = 102) over 9 years, individuals' breeding dispersal probability in relation to age, sex, and reproductive success wanalyzed via a generalized linear mixed effect modeling approach.Results: Our results show that 55% males and 51% females keep their previous territories following nesting success. Failed breeding attempts increased dispersal probabilities. Both females and males failed in breeding were more likely to disperse with greater distances than successful birds(females: 825 ± 216 m vs 196 ± 101 m, males: 372 Crested Ibis exhibited a female-biased dispersal pattern that the mean dispersal distance± 164 m vs 210 ± 127 m). of females(435 ± 234 m) was much larger than that of males(294 ± 172 m).Conclusion: Our results are fundamental to predict the patterns of breeding dispersal related to reproductive success under different release sites. From the conservation point of view, landscape connectivity between the reintroduced populations should be taken into account in accordance with the distance of breeding dispersal.

BLUP Estimation of Linear Mixed-effects Models with Measurement Errors and Its Applications to the Estimation of Small Areas

The linear mixed-effects model （LMM） is a very useful tool for analyzing cluster data. In practice, however, the exact values of the variables are often difficult to observe. In this paper, we consider the LMM with measurement errors in the covariates. The empirical BLUP estimator of the linear combination of the fixed and random effects and its approximate conditional MSE are derived. The application to the estimation of small area is provided. Simulation study shows good performance of the proposed estimators.

公路隧道入口区域驾驶人吸睛效应综合评价

为全面和系统评价公路隧道入口区域视觉吸引对驾驶人吸睛效应视觉表现的影响,本文招募30名被试开展自然驾驶实验,采集驾驶人在公路隧道入口区域不同视觉吸引条件下的眼动数据,基于因子分析法选取驾驶人吸睛效应敏感评价指标,并分别构建线性混合效应模型和数据包络分析模型,识别和探究公路隧道入口区域视觉吸引对驾驶人吸睛效应视觉表现的影响特征和作用机理。结果表明:因子分析结果显示,驾驶人吸睛效应敏感视觉指标为注视持续时间、瞳孔直径、扫视持续时间和扫视幅度;公路隧道入口区域不同视觉吸引条件对驾驶人吸睛效应的视觉表现和综合效率有显著影响,且受驾驶人年龄和驾驶经验的个体特质因素影响显著,而性别因素对其没有显著性影响;视觉吸引的存在均会不同程度地损害驾驶人的正常视觉绩效,降低其合理有效性;提示标语视觉吸引条件下,驾驶人的视觉注意水平最差,视觉认知负荷程度最高,吸睛效应的负面影响最大,广告牌条件次之。

基于在线更新的线性混合效应模型的参数估计

本文考虑在线更新数据集下线性混合效应模型的参数估计问题,提出了对应的在线更新估计方法,并证明了所得估计量的相合性.通过数值模拟发现,在不同的参数设置下,该方法的表现良好.将该方法与全局估计进行对比发现,虽然该方法在估计误差方面的表现不如全局估计,但是该方法能适用于在线更新数据集的情形,且大大降低了估计量的估计时间,以及估计时对计算机存储性能与计算性能的要求.

基于正交投影的线性混合效应模型的弹性网变量选择

本文考虑线性混合效应模型的变量选择问题.通过结合QR分解和弹性网惩罚方法,提出了一种线性混合效应模型中固定效应的变量选择方法.先通过QR分解技术消除随机效应对模型的影响,再利用弹性网构造固定效应的惩罚最小二乘目标函数,从而同时进行回归系数的估计和变量选择,证明了所得估计的组效应性质.所提出的变量选择过程不仅可以将固定效应和随机效应分离,使得两者之间互不影响,而且拥有弹性网方法的组效应性质.模拟研究了所提出方法的有限样本性质.

置信区间宽度等高线图在线性混合效应模型样本量规划中的应用

线性混合效应模型在分析具有嵌套结构的心理学实验数据时具有明显优势。本文提出了置信区间宽度等高线图用于该模型的样本量规划。通过等高线图,确定同时符合检验力、效应量准确性以及置信区间宽度要求的被试量和试次数。结合关注被试内实验效应和被试变量调节效应的两类典型模型,通过两个模拟研究,采用基于蒙特卡洛模拟方法,探索效应量、随机效应大小和被试变量类型对置信区间宽度等高线图及样本量规划结果的影响。

Simultaneous optimal estimates of fixed effects and variance components in the mixed model

For a general linear mixed model with two variance components, a set of simple conditions is obtained, under which, (i) the least squares estimate of the fixed effects and the analysis of variance (ANOVA) estimates of variance components are proved to be uniformly minimum variance unbiased estimates simultaneously; (ii) the exact confidence intervals of the fixed effects and uniformly optimal unbiased tests on variance components are given; (iii) the exact probability expression of ANOVA estimates of variance components taking negative value is obtained.

内蒙古大兴安岭林区白桦天然林单木胸径生长模型构建

【目的】为准确预测内蒙古大兴安岭林区的白桦天然林单木生长并制定适应性经营管理措施,构建包含气候因子和林木大小多样性因子的白桦单木胸径生长混合效应模型。【方法】数据来源于内蒙古大兴安岭林区第8和9次森林资源清查数据,共筛选出符合要求的固定样地97块,白桦样木4785株。基于筛选的数据,运用逐步回归法,构建传统单木胸径生长模型,并在此模型的基础上,引入样地随机效应,构建白桦单木胸径生长混合效应模型。利用十折交叉验证法分别对已构建的基础模型和混合效应模型进行检验。【结果】期初胸径的对数、大于对象木的断面积和、样地内胸径标准差、生长积温和年平均降雨量对白桦单木胸径生长量存在显著影响。与基础模型相比,混合效应模型的调整决定系数提高了0.1206,均方根误差降低了0.0971 cm2,模型的预测精度显著提高。十折交叉验证的结果表明混合效应模型同样表现出较好的拟合结果。【结论】包含气候因子和林木大小多样性因子的白桦单木胸径生长混合效应模型能精准预测白桦单木胸径的生长动态,可以为内蒙古大兴安岭林区的白桦天然林的科学经营提供支持。

高速公路能见度的时空特征及预测

利用开源的历史气象数据,分析湖南省高速公路网能见度的时空变化特征,探究影响地区能见度的气象要素相关性,并构建基于BP神经网络和广义线性混合模型(GLMM)的能见度预测模型,结果表明BP神经网络模型能够更好地利用当前时刻的气象要素数据预测3 h后的高速公路能见度数值。

脂肪肝和血脂异常二元响应混合效应模型及其应用

为了探究脂肪肝、血脂异常与各常规体检项目间的关系,实现对脂肪肝和血脂异常的发病风险评估,基于2 972例体检者9 091人次血常规体检结果建立以脂肪肝血脂异常为响应变量的二元响应广义线性混合模型,并进行疾病风险预测以及预测效果评价.结果表明:脂肪肝血脂异常的共同影响因素有性别、年龄、糖尿病、体质指数、谷丙转氨酶和高密度脂蛋白,脂肪肝和血脂异常两个响应之间的混合效应之间呈现一定的正相关性.在模型预测方面,模型中脂肪肝的ROC曲线下面积SAUC为0.855(95%CI:0.831~0.881),血脂异常的ROC曲线下面积SAUC为0.814(95%CI:0.794~0.850),五则交叉验证结果显示脂肪肝血脂异常的SAUC分别为0.850(95%CI:0.845~0.868)、0.807(95%CI:0.793~0.819),表明模型能够充分反映响应变量之间的相关性,具有较好的预测能力,适用于医学上多疾病的联合分析.

基于BP-L_(2)混合算法的线性混合效应模型在帕金森病语音信号中的应用

通过对帕金森病语音信号多重共线性纵向高维数据的预处理和分析,可为相关医疗机构提供重要信息。首先采用随机森林对数据进行预处理,得到降维数据集,通过相关性分析得知该数据存在多重共线问题;然后在BP神经网络中引入L_(2)正则化改变其目标函数,解决临床数据经常存在的数据多重共线性,以便更好地拟合线性混合效应模型;最后对比分析引入BP-L_(2)混合算法前后线性混合效应模型的AIC、BIC和-LogLik指标,证明引入该算法的优势。

大豆蛋白质含量相关QTL间的上位效应和QE互作效应

利用Charleston×东农594重组自交系构建的SSR遗传图谱及混合线性模型方法对2002—2006连续5年的大豆蛋白质含量进行QTL定位,并作加性效应,加性×加性上位互作效应及环境互作效应分析。共检测到10个控制蛋白质含量的QTL,分别位于第B2、C2、D1a、E和N连锁群,其中1个表现为遗传正效应,9个表现为遗传负效应,另检测到15对影响蛋白质含量的加性×加性上位互作效应的QTL,解释该性状总变异的13.75%。环境互作检测中,发现9个QTL与环境存在互作,贡献率达到4.47%。

他克莫司在中国肾移植患者中的群体药物动力学研究

本研究旨在考察口服他克莫司(tacrolimus)在中国肾移植患者中的群体药物动力学特征并探讨群体药物动力学参数和相关因素间的关系。研究中回顾性搜集了58例肾移植患者的802份他克莫司稳态全血样本资料。患者随机分为模型建立组(41例)和模型验证组(17例)。用非线性混合效应模型(NONMEM)程序中的一级评估法(first-order estimation,FO)对模型建立组的数据进行分析。计算清除率(CL/F)、表观分布容积(V/F)的群体典型值,定量评价人口统计学指标、生化指标和合并用药等固定效应因素对药物动力学参数的影响。单室一级吸收和消除模型能够较好地拟合数据。最终模型包含了移植术后时间(POD)、红细胞压积(HCT)、谷草转氨酶(AST)、合并使用佩尔地平(NICA)和地尔硫(DIL)等对CL/F的影响。用模型验证组数据进行验证的结果表明观测值和模型预测值之间没有明显的偏倚,模型的稳定性和准确度较好。CL/F和V/F的群体典型值分别为21.7 L.h-1和241 L;相应的个体间变异分别为41.6%和49.7%。观测值与预测值之间的残差SD为2.19μg.L-1。本文建立的模型可以为临床他克莫司剂量选择提供一定参考。

基于线性混合模型的落叶松枝条基径模型

以黑龙江省五营林业局丽林林场30株人工落叶松2 190个枝条基径数据为例,利用逐步回归技术建立了落叶松枝条基径模型:BD=b1+b2DINC+b3DINC2+b4DBH.DINC2。然后,利用S-PLUS软件中的LME过程,拟合线性枝基径模型。采用AIC、BIC、对数似然值和似然比检验等模型评价统计指标对不同模型的拟合效果进行比较分析。结果表明:当拟合枝条基径模型时,b1、b2、b3同时作为混合参数时模型拟合最好。为了矫正混合模型构建过程中产生的异方差现象,把幂函数和指数函数加入到枝条基径混合模型中。指数函数显著提高了枝条基径混合模型的拟合效果,并且消除了异方差现象。模型模拟表明:对于大小相同树木,枝条基径随着着枝深度(DINC)的增加而增大,对于大小不同的树木,枝条基径随着胸径(DBH)的增加而增大。林木的胸径变量很好地反映了不同大小树木的枝条基径的变化。在不知道详细林分信息的前提下,可以利用树木变量合理地预测兴安落叶松人工林的枝条基径的变化规律。