共查询到15条相似文献,搜索用时 78 毫秒
1.
本文目的是介绍复杂抽样调查设计多值名义资料一水平多重logistic回归模型构建,并探讨不同策略之间的差异。采用SAS中的LOGISTIC过程和SURVEYLOGISTIC过程,分别按照是否考虑抽样设计与是否考虑抽样权重共4种分析策略对数据构建广义logistic回归模型,并比较结果。不同分析策略所得结果显示,不仅参数估计值、回归系数标准误、OR值及其置信区间的估计值有所差别,而且对纳入模型的解释变量也有影响。因此,在对复杂抽样调查设计多值名义资料构建广义logistics回归模型时,既要考虑抽样设计,又要兼顾抽样权重,否则即使样本量足够大,也会导致错误的推断结论。 相似文献
2.
复杂抽样调查设计多值有序资料一水平多重Logistic回归分析 总被引:1,自引:1,他引:0
本文目的是比较不同分析策略对复杂抽样调查设计多值有序资料一水平多重logistic回归分析结果的异同。通过实例分析,利用四种不同的分析策略(将复杂抽样视为单纯随机抽样,考虑抽样设计不考虑抽样权重,考虑抽样权重不考虑抽样设计,同时考虑抽样设计和抽样权重)对复杂抽样设计多值有序资料进行建模。在四种不同分析策略的累积logistic回归模型拟合的结果中,自变量的偏回归系数、标准误差及P值均有所不同。在对复杂抽样调查设计的多值有序资料回归建模时,将抽样设计和抽样权重纳入统计分析,会得到更准确、更稳健的分析结果。 相似文献
3.
本文目的是介绍复杂抽样调查设计二值资料多重logistic回归分析方法。通过一个实例,利用八种不同的分析策略(不考虑抽样设计和抽样权重、考虑抽样设计不考虑抽样权重、不考虑抽样设计考虑抽样权重、同时考虑抽样设计和抽样权重以及分别不考虑与考虑派生变量)对数据进行建模。对所得结果进行比较得出如下结论:在对复杂抽样设计资料进行统计分析的过程中,同时考虑抽样设计和抽样权重可以得到符合数据内部变量间依赖关系真实情况的结论。此外,本研究还介绍了采用SAS软件中SURVEYLOGISTIC过程对复杂抽样调查数据进行多重Llogistic回归分析的详细步骤。 相似文献
4.
本文目的是全面介绍生存资料的特点及其常用统计分析方法。生存资料具有以下四个特点:①同时具有生存结局和生存时间;②生存时间可能含有删失数据或截尾数据;③生存时间的分布通常不服从正态分布,常呈指数分布、Weibull分布、对数正态分布;④影响生存时间的因素较复杂且不易控制。生存资料统计分析方法涉及统计描述、差异性分析和回归分析三大类,其中,统计描述主要有Kaplan-Meier(卡普兰-迈耶)估计法和Life table(寿命表)估计法;差异性分析主要有对数秩检验(log-rank test)和威尔考克森检验(Wilcoxon test);而回归分析主要有Cox比例和非比例风险回归模型、参数回归模型。在对生存资料进行统计分析时,需要合理选择统计分析方法,方可全面而又深入地揭示生存资料的内在变化规律。 相似文献
5.
6.
7.
目的本文目的是概述多重线性回归分析的核心内容与关键技术。其核心内容有以下四点:第一,构建多重线性回归模型的方法和求解参数的方法;第二,进行回归诊断的意义和方法;第三,筛选自变量的意义和方法;第四,评价模型拟合效果的方法。其关键技术是如何基于经典统计思想、贝叶斯统计思想和机器学习统计思想实现多重线性回归分析。 相似文献
8.
9.
目的分析客家人群颈动脉闭塞的临床特点,并分析其相关危险因素。方法选取我院收治的120例颈动脉闭塞患者及同期收治的120例非颈动脉闭塞的患者为研究对象,回顾性分析所有研究对象颈CTA、头颅MRI+MRA检查结果及甘油三酯(TG)、总胆固醇(TC)、低密度脂蛋白胆固醇(LDL-C)、高密度脂蛋白胆固醇(HDL-C)、血糖(Glu)、同型半胱氨酸(Hcy)、C反应蛋白(CRP)、糖化血红蛋白(HbA1c)等相关血生化指标,探讨客家人群颈动脉闭塞的临床特点及相关危险因素。结果 120例客家人群颈动脉闭塞患者中,前循环缺血表现93例(77.5%),后循环缺血8例(6.67%),无症状19例(15.83%),差异有统计学意义(P0.05);其中后交通动脉开放89例,前交通动脉开放45例,差异有统计学意义(P0.05)。颈动脉闭塞患者性别、年龄、TC、TG、LDL-C、HDL-C、CRP、HbA1c、Hey水平、冠心病病史、高血压史、糖尿病史与非颈动脉闭塞患者相比差异具有统计学意义(P0.05);LDL-C、Hcy、HbA1c、糖尿病史、高血压史、冠心病病史六项因素属于影响客家人群颈动脉闭塞相关危险因素。结论客家人群颈动脉闭塞以前循环系统缺血表现为主,主要表现为偏瘫、失语、偏身感觉障碍、头痛、发作性单眼盲(黑蒙);少数后循环缺血的临床表现为反复头晕或突发晕厥;后交通动脉为其主要代偿方式;LDL-C、Hcy、HbA1c、糖尿病史、高血压史、冠心病病史六项因素属于影响客家人群颈动脉闭塞相关危险因素,在颈动脉闭塞中发挥重要作用。 相似文献
10.
本文目的是介绍一种能很好地拟合具有间断点资料的方法。当资料中具有明确的间断点或整个资料包含多段不同变化趋势的曲线类型时,为了提高曲线回归模型对资料的拟合优度,需要充分发挥"节点"的作用。可基于两种不同视角来利用"节点":其一,人为设定不同数目的节点,利用样条变换方法拟合分段多项式曲线;其二,在客观存在的节点上,求曲线的一阶乃至四阶导数,并据此构建曲线回归模型。得到的结论是:后者的拟合效果优于前者。 相似文献
11.
12.
Christopher R.P. Lind Jason A. Correia Andrew J.J. Law Ritwik Kejriwal 《Journal of clinical neuroscience》2008,15(8):886-890
The objective of this paper is to characterise the frequency of different surgical techniques for targeting the lateral ventricle in shunt surgery and the attitudes of Australasian neurosurgeons and advanced neurosurgical trainees to stereotactic adjuncts. Secondarily, we aim to learn from and collate the practical experiences of neurosurgeons for those attempting to improve their operative success. A survey of all practising and training members of the Neurosurgical Society of Australasia (NSA) was conducted. One hundred and eleven surveys were completed generating an overall response rate of 57%. Of those 108 performing shunt surgery, 10 (9%) preferred a frontal approach and 70 (65%) a posterior approach to the frontal horn. Twenty-seven neurosurgeons (25%) preferred the posterior approach to the atrium or body of the lateral ventricle. A wide range of burr hole sites and targeting landmarks were described and are discussed. There was no consistent pattern for neurosurgeons changing their preferred approach during their careers. Seventy-five per cent of respondents make adjustments to measurements for children by a wide range of methods. Frameless or frame-based stereotaxy is used at times by about half of all neurosurgeons. Posterior approaches to the lateral ventricle using freehand techniques are preferred among NSA members and their trainees but there are a wide variety of landmarks used. Many of these techniques have been developed over years of operative experience and could be modelled with planning software to assess their theoretical merits. There is no evidence of the uptake of generic accuracy guides but there is evidence of significant exposure to frameless stereotactic techniques that may grow in popularity as the technology improves. 相似文献
13.
14.
Lieven Lagae 《Epileptic Disord》2014,16(Z1):S44-S49
An historical overview is provided regarding the use of benzodiazepines for the treatment of acute prolonged convulsive seizures. It is clear that intravenous benzodiazepines remain a first step for the in‐hospital treatment of prolonged seizures or status epilepticus. However, in the community, in a pre‐hospital situation, intravenous administration is not possible. In recent years, it was shown that rectal, buccal, intranasal, and intramuscular administration of benzodiazepines is very effective as a first and safe treatment step. In many cases, rectal diazepam is not socially acceptable anymore, and therefore more emphasis is now put on buccal, intranasal, and intramuscular administration. At present, based on the available data, midazolam is the product of choice for the acute treatment of prolonged convulsive seizures. 相似文献
15.
Karthik Suresh Sanjeev V. Thomas Geetha Suresh 《Annals of Indian Academy of Neurology》2011,14(4):287-290
Statistical analysis is an essential technique that enables a medical research practitioner to draw meaningful inference from their data analysis. Improper application of study design and data analysis may render insufficient and improper results and conclusion. Converting a medical problem into a statistical hypothesis with appropriate methodological and logical design and then back-translating the statistical results into relevant medical knowledge is a real challenge. This article explains various sampling methods that can be appropriately used in medical research with different scenarios and challenges. 相似文献