Practical Medical Statistical Analysis with Python

Name: Practical Medical Statistical Analysis with Python
ISBN: 9787117341417

潘兴强 / 陈根浪Apr 2025

3.5

Word count: 86K words
Chapters: 84
ISBN: 9787117341417

Report an error Find this book

Summary

This book introduces the grammar foundations related to data analysis in a highly targeted way, helping readers get started quickly. For example, Part 2 focuses on Python入门语法、特征以及数据分析所需要的一些基本语法。Python can achieve the same goal through multiple libraries and methods—for instance, linear regression can be implemented with libraries such as sklearn and statsmodels, and survival analysis with lifelines, pysurvival, statsmodels, and others—and code often varies widely, which confuses beginners. To address this, the book mainly uses the Scipy library for hypothesis testing and the statsmodels library for fitting statistical models, striving to complete data analysis with concise code. For example, Part 7 explains how to use the Pandas library to simultaneously complete data cleaning and statistical plotting, reducing the amount of code and improving data analysis efficiency.

The book emphasizes practicality in its writing, focusing on combining preliminary data processing with medical statistical analysis; it introduces statistical methods by data type, helping readers quickly find the corresponding statistical method in actual data analysis; when introducing each statistical method, it stresses applicable conditions, provides the most complete code, and emphasizes interpretation of statistical results, highlighting practicality and operability to reduce the difficulty of data analysis.

Editor's review

This book addresses the practical needs of medical data analysis, combining an introduction to Python syntax with medical statistical methods and emphasizing “can use it, can explain it.” To tackle the common beginner problems of too many libraries and inconsistent code, the author explicitly uses Scipy for hypothesis testing, statsmodels for fitting statistical models, and Pandas to simultaneously complete data cleaning and statistical plotting, reducing code volume and improving efficiency. The book organizes statistical methods by data type, making it easy to quickly find the corresponding method when facing real data; each method emphasizes applicable conditions, provides fairly complete code, and explains statistical results, highlighting operability. Its strength lies not in piling up syntax but in unfolding around the data processing workflow in medical research, making it suitable for clinical and public health personnel who need to do their own statistics to learn and use on the go. When reading, it is recommended to practice with real data: first get the code running, then understand the applicable conditions, and avoid merely copying code without judging the method.

Who it's for

A good fit for

Clinical doctors and researchers who need to complete medical data statistical analysis themselves
Students and researchers in public health and epidemiology who hope to use Python to replace some traditional statistical software
Beginners with some statistical background who want to systematically learn Python medical data analysis
Master's and doctoral students who need to process clinical data and draw statistical charts

Not a good fit for

Complete beginners with no statistical foundation and no exposure to any programming language
Readers who hope to deeply study Python software engineering and the principles of machine learning algorithms
Analysts who only need ready-made statistical software point-and-click operations and do not plan to write code

Reading tips

First read through the syntax foundations in Part 2 to ensure you can understand the subsequent code before entering the statistics chapters
Jump directly to the chapter on the corresponding statistical method according to your data type, and run the example code locally while reading
For each method, first confirm the applicable conditions before applying the code, and explain the results in the way shown in the book
Prepare a small medical dataset of your own and practice data cleaning and plotting in sync with chapter progress

版权信息
前言
1 Python简介与安装
1.1 Python的优点
1.2 Python的安装与配置
1.3 Anaconda的使用方法
1.4 Jupyter Notebook
2 Python语言基础与重要的库
2.1 Python快速入门
2.2 Python语法基础
2.3 重要的Python库
3 数据集创建
3.1 NumPy多维数组对象
3.2 Pandas数据结构
3.3 数据取值与选择
3.4 数据读取与存储
4 基本数据管理
4.1 数据基本信息与结构查看
4.2 创建新变量
4.3 变量重命名
4.4 数据类型转换
4.5 数据排序
4.6 缺失值处理
4.7 缺失数据填补
4.8 重复数据处理
4.9 数据集的合并
4.10 数据集取子集
4.11 数据分组
4.12 melt()函数
4.13 数据集更新
5 高级数据管理
5.1 控制流
5.2 函数
5.3 向量化字符串操作
5.4 正则表达式
6 网络数据采集
6.1 初识爬虫
6.2 http协议与url
6.3 网页结构
6.4 Requests库
6.5 BeautifulSoup库
7 资料类型及展示
7.1 资料类型
7.2 统计描述
7.3 数据透视表
7.4 表格重塑
7.5 绘制图形
8 定量资料统计方法
8.1 单样本资料与已知总体参数比较
8.2 两组资料之间的比较
8.3 两组以上资料比较
8.4 相关分析
8.5 线性回归分析
9 分类资料数据分析
9.1 卡方检验
9.2 Fisher确切概率法
9.3 配对卡方检验
9.4 多个相关样本的非参数检验（Cochran Q检验）
9.5 趋势卡方检验
10 多重线性回归
10.1 多重线性回归分析
10.2 自变量筛选
10.3 多重共线性和回归诊断
11 logistic回归
11.1 二分类logistic回归
11.2 有序logistic回归
11.3 无序多分类logistic回归
11.4 条件logistic回归
12 Poisson回归
12.1 Poisson回归的应用条件
12.2 资料格式
12.3 利用广义线性模型实现Poisson回归
13 生存分析
13.1 基本概念
13.2 生存分析研究的主要内容
13.3 生存率的估计与组间比较
13.4 中位生存时间与生存曲线
13.5 Cox比例风险模型
14 时间序列分析
14.1 时间序列的预处理
14.2 平稳时间序列建模
14.3 非平稳时间序列预处理
14.4 ARIMA模型
14.5 季节性ARIMA模型

FAQ

Can readers with no programming background understand this book?

Part 2 of the book is specifically devoted to introductory Python syntax and the basic syntax needed for data analysis, catering to beginners. However, if you have never been exposed to programming at all, it is advisable to first spend time practicing basic syntax and Pandas operations before moving on to the statistical modeling chapters; otherwise, you may easily remain at the level of copying code.

Why does the book consistently use Scipy and statsmodels?

Because in Python there are often multiple libraries for achieving the same goal, and the code is not uniform, which can easily confuse beginners. This book consistently uses Scipy for hypothesis testing and statsmodels for fitting statistical models, and strives to complete analyses with concise code, so that readers can develop stable operating habits and reproducible analysis workflows.

Can the code in the book be used directly on my own data?

The book provides fairly complete code and result interpretations that can serve as templates for reference. However, actual data often differ in variable types, missing values, and grouping structures, so you need to first perform data cleaning and check applicable conditions according to the methods in the book, and then adjust the code; you cannot apply it directly without judgment.

Comments

Find this book

This site is an index: you start “Search all sources” in your browser, and the entries it lists all point to third-party sites; please judge their availability yourself.

About the author

潘兴强 Author

Pan Xingqiang: publicly available information is limited. At present, only one work by this author is known, Python Medical Practical Statistical Analysis, classified under medicine. The title suggests that the author writes for practical statistical analysis in the medical field, attempting to combine the Python programming tool with the data-statistics needs of medical research. Medical statistics involves study design, data processing, and interpretation of results, and places high demands on methodological accuracy and operability. By approaching the subject through Python, the author indicates attention to the practical application of programming technology in medical data handling rather than a purely theoretical introduction. Because only this one work is included and no information on the author's life or professional background appears in the available materials, no further judgment can be made about his academic experience or the full range of his writing. Readers may regard the book as a tool-oriented volume for applied medical statistics, while its specific content and style require consulting the original work.

陈根浪 Author

Chen Genlang is an author about whom limited public information is currently available. His representative work is Practical Statistical Analysis in Medicine with Python, which is classified under medicine in our catalog. The book indicates that the author focuses on applying the Python programming language to statistical analysis in medical practice, and it is likely intended for medical researchers, clinical practitioners, and others who need to handle medical data. The work belongs to the practical genre at the intersection of medicine and data analysis, placing greater emphasis on concrete methods and operational feasibility than on abstract theoretical exposition. Since only one of his works is included in our catalog, and his nationality, dates of birth and death, educational background, and professional positions cannot be confirmed, this profile makes no speculation about his personal history. Overall, Chen Genlang's writing reflects the real demand in medical research for using programming languages to carry out data processing and statistical analysis, and offers practical reference value; a fuller picture of his academic profile awaits more public information.