生物实验数据的单因素方差分析

结合实例详细地叙述了生物学实验数据的单因素方差分析计算方法,介绍了根据计算结果如何分析组群间的差异显著性,具有较强的实用意义。     

生物实验数据的单因素方差分析

结合实例详细地叙述了生物学实验数据的单因素方差分析计算方法,介绍了根据计算结果如何分析组群间的差异显著性,具有较强的实用意义.     

SPSS方差分析在生物统计的应用

方差分析是生物统计中常采用的一种方法。如何使用统计分析软件进行方差分析来实现对研究结果的快速和科学的处理,获得正确的结论,是生物学研究中重要的一环。本文通过实例介绍了如何使用SPSS(Statistical Package for the Social Science or Statistic Products and Service Solution)数据分析工具进行方差分析的方法;实现了数据分析和处理的快捷、准确和直观;与Excel相比,SPSS的统计分析功能更为强大,既有利于提高数据处理效率,又降低了实验成本。     

计算机在生物机能实验方面的几个应用

使用传统机器的目的是为了节省人力,而计算机的应用则是对人脑能力提供帮助。随着社会经济的发展,计算机将日益渗透到人类社会生活的各个领域并将发挥越来越重要的作用。     

正常SD大鼠的部分生物数据测定

本文报道３—８月龄,体重２００—６００ｇ、健康Ｓｐｒａｇｕｅ—Ｄａｗｌｅｙ大鼠的血液常规检查、血液生化分析、主要脏器重量及脏器系数测定结果,并探讨了现有文献间提供的大鼠生物学数据存在差异的原因,以供有关科研人员参考。     

带噪生物实验数据的不确定支持向量数据描述

在对候选基因进行排序时,支持向量数据描述（SVDD）可以用来描述各种异构的数据源,如序列数据、学术文献数据、各种生物实验数据等。由于生物实验数据带有噪声,在用SVDD对其描述时,会遇到噪声的影响。本研究通过公式推导扩展了原始的SVDD,提出不确定支持向量数据描述（USVDD）,用来降低噪声的影响。利用酵母基因表达数据进行实验,结果表明该方法比标准的SVDD对带噪声的数据具有更好的描述能力。     

实验动物生物学特性数据的分类编码

参照国家“实验动物资源共性描述规范”的数据分类原则,以实验动物所包含的基本信息、遗传数据、生理数据、生化数据、解剖数据等五大生物学特性数据种类进行划分,采用层级结构探索了一套灵活性、可扩展的实验动物生物学特性数据动态分类编码方法,该方法对实验动物数据资源的科学保存、有效共享和科学管理具有重要的支撑作用。     

多元方差分析中的单一自由度独立比较

本文根据一元方差分析的单一自由度比较原理提出了多元方差分析中的单一自由度比较方法,以用于各种平衡试验设计中具多个变量的处理间多重比较．     

实验数据的统计分析与科研论文的撰写

几乎所有的实验的结果,包括有非常明显的实验效果的实验结果,都需要用适当的统计分析方法进行评价。数据的分析应主要围绕研究的目的进行,对实验的假设进行验证。同时,数据分析的主要目标是提取数据中所有能被解释的有用信息,考虑生物的变异和实验所产生的误差对研究结果的影响,尤其是防止抽样误差对于实验（治疗）效果的错误判断的重要工具。当然,也存在统计学有显著性差异,而不存在生物学意义的现象。因此,在撰写科研论文时,既要有正确的实验设计和使用正确的资料统计分析方法,又要准确描述和解释实验结果。     

苦丁茶冬青的RAPD影响因素及实验条件的优化

以苦丁茶冬青为材料研究随机扩增多态DNA(RAPD)的影响因素及各种实验条件优化。研究结果表明：模板DNA的浓度适宜范围为20ng／反应-80ng／反应RAPD均可得到一致的结果;dNTVs的适宜浓度范围为200μmol／L-400μmol／L;Mg^2 适宜浓度范围为1．5mmol／L-2．0mmol／L;其合适的复性温度为35—37℃;2min的延伸时间,45次热循环。按照此优化的RAPD条件进行重复实验,实验结果重现性良好,因而确定了苦丁茶冬青RAPD反应体系之最佳的实验条件。     

Linear Discriminant Functions and Problems of Hybridization

A discriminant analysis method for frequency data for hybridization based on weighted multivariate analysis of variance is given for allotting an individual to one of groups.     

Profile Analysis of Variance as a Tool for Analyzing Correlated Responses in Experimental Ecology

In ecological studies experiments are often designed in which the variables to be compared are not statistically independent. Examples include repeated measures of the same response by the same individual at different times, measurement of several traits on the same individual, and measurements taken from two or more types of organisms present together in the same experimental unit (e.g.) plot, cage, pond, etc.). This type of design violates several assumptions of the standard analysis of variance. These assumptions are examined and profile analysis, a modification of the standard analysis of variance which does not depend upon these assumptions, is presented. Simple instructions for performing profile analysis of variance using two common statistical packages for mainframe computers are provided in an appendix.     

The Polynomial Model in the Multivariate Analysis of Variance

Assuming that the independent variables (factors) are quantitative, there exist besides the coding schemes generally used for the multivariate analysis of variance (dummy-coded or effect-coded design matrices) the so-called polynomial models. The advantage of these polynomial models are the full rank design matrices, which allow a more comprehensible analysis, i.e. the unambiguous interpretation of tested hypotheses and simultaneous confidence intervals.     

Stein's Two-Stage Test in Linear Models

After a brief presentation of Stein's two-sample test there is shown an improved procedure for general linear hypotheses analogous to the improvement of the two-sample-t-test described by Stein. The example of an analysis of variance in an one-way layout demonstrates the execution of the procedure as well as the problems that occur with the determination of the test parameters n₀ and z. For these problems there is finally suggested a practicable way of solution.     

An application of experimental design using mutually orthogonal Latin squares in conformational studies of peptides

We address the question-can we use experimental design methods to investigate peptide conformation and identify conformational parameters that may contribute more significantly to the potential energy than others? We used mutually orthogonal Latin square design to sample the conformational space of peptides and analysed the samples using analysis of variance. We examined the equality of the effect of the torsion angles on the conformational potential energy. The results showed that different torsion angles contributed differently to the conformational energy. We are able to identify those parameters that may have to be more carefully considered in conformational studies of peptides.