目录
目录
摘要II
关键词II
AbstractIII
引言
1选题背景1
1.1课题研究的目的与意义 1
1.2国外研究进展 1
1.3课题应用前景2
2文献综述3
3方案论证 5
3.1广义线性模型（GLM）介绍 5
3.2常用的广义线性模型 5
3.3广义线性模型在研究离散型数据方面的优点 6
4 实验过程与结果分析 7
4.1离散型模拟数据的生成 7
4.2模型的选取 7
4.3实验结果11
4.4对实验结果的分析及展望 13
致谢16
参考文献17
GLM分析方法在离散型数据处理上的应用分析
摘 要
广义线性模型（GLM）是统计分析模型中使用最广泛的统计模型之一,其模型特点是不强行改变数据的自然度量，数据可以具有非线性和非恒定的方差结构。它是经典线性模型的自然推广,在医学、生物、保险和经济、社会数据的统计分析领域中具有重要的意义。由于广义线性模型包含有许多有不同类型的模型，及其所具有的许多优良性质使其在实际问题中的应用越来越普遍，目前该模型即可以适用于连续型数据，又可以分析离散型数据。近年来，广义线性模型对离散型数据分析的速度与估计的准确度也得到了提升。基于此，本文前两章主要介绍GLM分析方法在离散型数据分析的现状以及广义线性模型的基本理论相关内容。第三章论证了GLM分析方法在分析离散型数据方面的可行性。第四章设计模拟实验，基于线性模型产生服从正态分布与均匀分布的多组离散型表型数据和基因型数据。使用GLM分析方法对模拟数据进行分析，通过比较分析结果，总结GLM方法对离散型数据分析的优缺点，并总结GLM分析方法在离散型数据处理上具有一定的优势，同时还存在着进一步优化的空间。
APPLICATION OF GLM IN DISCRETE DATA PROCESSING
ABSTRACT
Generalized linear model (GLM) is one of th *51今日免费论文网|www.51jrft.com +Q: ^351916072^ 
e most widely used statistical models in the statistical analysis model. The characteristics of GLM is that it does not force to change the natural measurement of data, and the data can have nonlinear and unsteady variance structure. It is a natural extension of the classical linear model, which is of great significance in the fields of medicine, biology, insurance, and statistical analysis of economic and social data. Because the generalized linear model contains many different types of models, and its many excellent properties make its application in practical problems more and more common. At present, the model can be applied to both continuous data and discrete data. In recent years, the speed and accuracy of generalized linear model for discrete data analysis have been improved. Based on this, the first two chapters of this paper mainly introduce the current situation of GLM in discrete data analysis and the basic theory of generalized linear model. The third chapter demonstrates the feasibility of GLM in analyzing discrete data. In the fourth chapter, the simulation experiment is designed to generate multiple groups of discrete phenotype data and genotype data which obey normal distribution and uniform distribution based on the linear model. The GLM analysis method is used to analyze the simulation data. By comparing the analysis results, the advantages and disadvantages of the GLM method to the discrete data analysis are summarized. The GLM analysis method has certain advantages in the discrete data processing, and there is still room for further optimization.

原文链接：http://www.jxszl.com/jsj/sxtj/606716.html