多元回归分析中离散变量的几种定量化方法

本文介绍离散变量(定性和等级变量)的三种定量化方法。经这些方法定量化后,多元回归分析的目的分别为将各类别(或等级)的依变量:1)与某一参照类别(或等级)比较;2)与各类别(或等级)的平均水平比较;3)与相邻类别(或等级)比较。本文通过两个实际例子阐述这些定量化方法的适用条件,在回归分析中的意义和优缺点。     

连续变量分析中的数据校正方法

连续变量分析中的数据校正方法陈伟胡永华在流行病学研究中两个或多个样本均数相互比较时，经常会遇到混杂因素或不均衡因素的影响，导致分析结果的偏差，甚至得出错误的结论。连续变量混杂因素控制方法很多，例如，在选择样本时注意保持两组研究对象均衡可比，在资料分析...     

连续变量的频率密度图的绘制方法研究

就国内医学统计学教材介绍的频数分布图绘制方法进行了探讨，并提出了一种绘制频率密度图的改进方法。     

连续变量诊断试验数据的ROC分析

目的 介绍一种连续诊断变量的ROC回归模型，以及在独立和相关结构下的参数估计方法，给出参数误差估计的Bootstrap方法。方法 应用SAS软件中的GENMOD过程和SAS语言编写的程序实现上述过程，并通过实例说明其应用效果。结果 利用ROC曲线方程，可以扣除协变量对诊断试验结果评价的影响，并能够计算出在不同协变量取值下的ROC曲线下面积，提供更为丰富和可靠的信息。结论 文中给出的ROC回归模型可以有效地用于连续变量诊断试验数据的ROC分析。     

正常眼与弱视眼视觉诱发电位波形的自动判别分析

提出了一种用于判别不同类型视觉诱发电位波形的频域判别分析法，并把此法用于正常眼和弱视眼视觉诱发电位波形的判别分析。它计算诱发电波形第一至第六次谐波的幅度和相位，把这十二个参数作为判别分析的自变量，再用31只正常眼和31只弱视眼的诱发电位波形数据建立判别分析系统。临床数据检验表明，本判别分析系统可较准确地判别正常眼和弱视眼的诱发电位波形。     

应用判别分析方法筛检高危险人群的探讨

本文采用逐步判别分析方法,探讨了应用病例-对照研究数据和结果建立判别用数学模型的方法,以期筛检高危险人群。结果表明,采用数学模型筛检高危险人群的办法对于开支大的群体研究课题具有显著的经济效益,而且由于样本的适度变小,有利于进行质量控制和观察管理。本方法在低发病率疾病的预防措施研究领域里具有较大的实用性和经济效益。     

基因表达数据的随机森林逐步判别分析方法

目的给出一种新的随机森林算法,它能在建模过程中自动对变量进行筛选,建立“最优”判断模型。方法采用变量重要性评分和逐步迭代算法选择有作用的变量;通过实际基因表达数据考核其应用效果,并使用R语言编程做模拟试验验证其有效性。结果三种疾病基因表达数据的判别模型,在包含很少量的基因情况下便获得了理想的分类效果;模拟试验则显示在类间区分度较大的情况下,随机森林逐步判别分析的效果明显,能有效地将有作用的变量保留在模型中,提高模型的判别效果;在类间区分度不够大的情况下分类效果提高不明显。结论随机森林逐步判别分析可以有效地应用于基因表达数据的基因筛选和分类研究,但要特别注意由随机波动对分析结果造成的影响。     

随机森林的变量捕获方法在高维数据变量筛选中的应用

目的探讨随机森林(RF)的变量捕获方法在高维数据变量筛选中的应用。方法通过模拟实验和实际数据分析,对两种变量捕获(vh.md,vh.vimp)和逐步剔除方法(var SelRF)进行比较,并通过选入变量的数目、模型预测错误率(PE)和受试者工作特征曲线下面积(AUC)对其进行评价。结果模拟实验表明,在变量具有联合作用、交互作用和弱独立作用情况下,变量捕获方法均明显优于var SelRF方法和全变量VIMP排序方法;实际数据分析结果表明,变量捕获方法筛选变量结果稳定,并能够保证良好的预测效果。结论变量捕获方法适用于高维数据的变量筛选,具有实用价值。     

定性变量的数量化方法新探

目的 传统意义上的品质变量的数量化方法是引入虚拟变量.但是,当遇到一些无法观察或有多种结果表述的定性变量时,这一方法就无法解决品质变量的数量化问题了.本文试图运用比较量化方法来解决这一难题,运用比较量化方法将需要量化的定性变量数量化.方法 首先选取与要量化的定性变量相近或者是等价的定量变量进行替换或转化,再通过求该定量变量的样本平均值,用定量变量样本值与其样本平均值进行比较,将需要量化的定性变量以＂比较方法＂为媒介过渡到虚拟变量,将定量变量样本比较结果用虚拟变量的赋值进行对应表示,实现需要量化的定性变量的数量化需要.结果 实证结果表明：经过比较量化方法处理后的妇女健康意识在健康教育层面上可以从定量角度有效地得到反映.同时也为进一步的定量分析研究做好铺垫.结论 比较量化方法可以高效地在各种统计分析过程中满足需要赋值的定性变量的量化分析需要.尤其是可以方便地将定性变量在经过比较量化处理后以虚拟变量的形式融入到逻辑回归模型的构建过程中.     

多个二项反应变量多水平因子分析模型的原理及应用

目的探讨多个二项反应变量多水平因子分析模型的应用。方法在MLwiN2．02软件中，采用马尔科夫链一蒙特卡罗参数估计方法，通过实例模拟及分析，说明模型的实际应用。结果该模型适用于反应变量为二项分类的、具有层次结构的数据。结论多个二项反应变量多水平因子分析模型有其独特的意义和用途。     

运用CQI改进护理品质的问题与对策

目的探讨护理CQI项目开展中存在的问题及对策。方法应用回顾性分析方法,对2013年全院各护理单元开展的CQI项目进行分析,发现存在的问题,分析原因、提出相应的对策。结果全院65个CQI项目,由科室正护士长或主持工作的副护士长组织开展,其中任职1~3年的护士长存在问题较多,护士长群体对质量管理工具选择单一、使用不熟练,团队协作意识不够。结论对护士长进行QCI专业培训,加强新上岗护士长质控能力的培训,建立团队质量改进的激励机制,能提高护士长运用质量管理工具的能力,提升护理质量。     

Two Kinds of Items in Quality of Life Instruments: ‘Indicator and Causal Variables’ in the EORTC QLQ-C30

Two kinds of variables may be differentiated within instruments measuring health-related quality of life (HRQOL). Physical symptoms may be called causal variables because their occurrence can cause a change in HRQOL, but poor HRQOL need not necessarily imply that a patient suffers from these symptoms. Other items can be regarded as indicator variables. They reflect the level of HRQOL and a patient with a poor HRQOL is likely to have low scores on all indicator variables. The aim of this study was to test the relationship of the latent HRQOL construct to items and domains on the EORTC QLQ-C30. Confirmatory factor analysis was performed on EORTC QLQ-C30 data from 205 gastrointestinal cancer patients assessed one month after surgery. Functioning scales were established as variables indicating the level of HRQOL whereas all other subscales and items were established as variables causing a change in HRQOL. The model-data fit was satisfactory. Results support the hypothesis that two kinds of variables may be differentiated within HRQOL instruments. Further research should investigate whether both kinds of variables could be combined into a higher order, aggregate score for HRQOL.     

Longitudinal Data Analysis. A Comparison Between Generalized Estimating Equations and Random Coefficient Analysis

The analysis of data from longitudinal studies requires special techniques, which take into account the fact that the repeated measurements within one individual are correlated. In this paper, the two most commonly used techniques to analyze longitudinal data are compared: generalized estimating equations (GEE) and random coefficient analysis. Both techniques were used to analyze a longitudinal dataset with six measurements on 147 subjects. The purpose of the example was to analyze the relationship between serum cholesterol and four predictor variables, i.e., physical fitness at baseline, body fatness (measured by sum of the thickness of four skinfolds), smoking and gender. The results showed that for a continuous outcome variable, GEE and random coefficient analysis gave comparable results, i.e., GEE-analysis with an exchangeable correlation structure and random coefficient analysis with only a random intercept were the same. There was also no difference between both techniques in the analysis of a dataset with missing data, even when the missing data was highly selective on earlier observed data. For a dichotomous outcome variable, the magnitude of the regression coefficients and standard errors was higher when calculated with random coefficient analysis then when calculated with GEE-analysis. Analysis of a dataset with missing data with a dichotomous outcome variable showed unpredictable results for both GEE and random coefficient analysis. It can be concluded that for a continuous outcome variable, GEE and random coefficient analysis are comparable. Longitudinal data-analysis with dichotomous outcome variables should, however, be interpreted with caution, especially when there are missing data.     

连续性肾脏替代治疗与间歇性血液透析治疗重症急性肾衰的比较研究

目的 对比分析在重症急性肾衰治疗上运用连续性肾脏替代治疗方法与间歇性血液透析治疗方法的临床效果.方法 选择自2010年1月-2012年3月在该院接受治疗的500例重症急性肾衰患者,分成实验组和对照组各250例,实验组患者选择连续性肾脏替代治疗[1],对照组患者选择间歇性血液透析治疗,经过一段时间的治疗后对比实验组和对照组患者治疗前后血清肌酐(Scr)、尿素氮(BUN)、内生肌酐(Ccr)的水平的变化;并对2组患者进行调查随访,比较1年后的存活率.结果 比较结果发现实验组患者在Scr、BUN、Ccr方面的改善明显好于对照组,2组比较差异具有统计学意义(P＜0.05);同时随访调查显示实验组患者的1年存活率也显著优于对照组,分别为82.4％和52.5％,2组比较差异具有统计学意义(P＜0.05).结论 与间歇性血液透析治疗相比,连续性肾脏替代治疗具有临床效果好、患者存活率高等优点,临床意义十分重要.     

线性模型中自变量相对重要性优势分析法估计及其应用

目的在多元线性回归模型中,估计各自变量的相对重要性,并探索区间估计方法。方法在自变量间存在相关时,运用Budescu(1993),Azen(2003)提出的优势分析法估计肝手术病例预计存活时间的影响因素重要性,并运用Bootstrap法探索区间估计方法以此来评价估计结果的变异性。结果血凝素、预后指数、酶功能对预计存活时间的相对贡献分别为0.1415、0.3408和0.490,其Bootstrap法95%可信区间分别为(0.0573,0.2744)、(0.2359,0.4545)和(0.3411,0.6090)。结论酶功能对肝手术病例预计存活时间的影响最大,预后指数次之,血凝素最小。当自变量间存在相关时,优势分析法估计的自变量相对重要性结果更精确稳定,值得推广应用。     

连续热镀锌及彩涂带钢簿板建设项目职业病危害因素识别与分析

目的通过对连续热镀锌、彩涂板生产建设项目职业病危害因素分析,探讨职业病危害因素分析识别的方法。方法依据国家职业卫生规范和标准,对本市5个连续热镀锌板、彩涂板项目职业病危害因素识别部分进行对比分析。结果连续热镀锌、彩涂板生产建设项目主要职业病危害因素为噪声、高温及热辐射、锌及氧化锌烟、铬酸、有机溶剂等。结论对建设项目进行细致的工程分析,以提高职业病危害因素的识别技术。     

Analyzing and Critiquing Occupational Therapy Practice Models Using Mosey's Extrapolation Method

ABSTRACT

Over time, there has been a persistent gap between theory and practice in occupational therapy. In this paper, it is suggested that this gap could be decreased by enhancing therapists' knowledge and understanding of the nature of theory. Mosey's (1996a) 9-step extrapolation method of developing theoretical conceptual practice models is proposed as one way of improving clinicians' understanding of the structure of theoretical conceptual practice models and knowing how to analyze and critique them to determine their usefulness in specific clinical contexts. This understanding will hopefully translate into increased utilization of theoretical conceptual practice models to guide every day practice.     

A Novel Method for Detecting Association Between DNA Methylation and Diseases Using Spatial Information

DNA methylation may represent an important contributor to the missing heritability described in complex trait genetics. However, technology to measure DNA methylation has outpaced statistical methods for analysis. Taking advantage of the recent finding that methylated sites cluster together, we propose a Spatial Clustering Method (SCM) to detect differentially methylated regions (DMRs) in the genome in case and control studies using spatial location information. This new method compares the distribution of distances in cases and controls between DNA methylation marks in the genomic region of interest. A statistic is computed based on these distances. Proper type I error rate is maintained and statistical significance is evaluated using permutation test. The effectiveness of the SCM we propose is evaluated by a simulation study. By simulating a simple disease model, we demonstrate that SCM has good power to detect DMRs associated with the disease. Finally, we applied the SCM to an exploratory analysis of chromosome 14 from a colorectal cancer data set and identified statistically significant genomic regions. Identification of these regions should lead to a better understanding of methylated sites and their contribution to disease. The SCM can be used as a reliable statistical method for the identification of DMRs associated with disease states in exploratory epigenetic analyses.