Pages: 59

This chapter deals with an introduction to data science, biostatistics, and R-programming language. The use of R is an essential requirement of this book. Therefore, the objectives are to introduce the process of installing R into user’s computer and to provide an outline of the basics of data science and biostatistics.

Pages: 30

In Chapter 1, we introduce data science and how it is interrelated with the discipline of statistics, including biostatistics and public health. However, it is significant to know what biostatistics as a field of knowledge is and how it operates with the modern world’s sophisticated data. It has been a usual practice for a modern student or scientist to spend time in searching materials in biostatistical techniques with examples and computing programming codes. There are no texts so far that may sufficiently fill the necessities of modern students, especially in biological sciences programs. Therefore, this chapter aims to provide insight to understand biostatistics and some of its essential concepts with relevant contemporary examples. Moreover, this chapter includes the process of data analysis and linking with the further chapters.

Pages: 32

This chapter will equip public health professionals with the essential tools and techniques to summarize and present data effectively. It will empower readers to extract meaningful insights from complex datasets and communicate their findings accurately, thereby contributing to evidence-based decision-making and further advanced analysis by providing a comprehensive overview of summary statistics and their graphical representations. This chapter begins by introducing the concept of summarization of data and its significance in data analysis. Subsequently, different types of summary statistics and their application in public health are discussed. This chapter also introduces the readers to the concept, importance, and different techniques of data presentation through public health–related examples. R-code and output for all examples are provided for the convenience of readers. Moreover, exercises are given so that readers can practice.

Pages: 27

In Chapter 3, many traditional data presentation and visualization techniques are discussed. The conventional methods are employed for representing either a single-variable or bivariate association; nevertheless, these approaches fall short in illustrating relationships among more than two variables. Moreover, as datasets in any field, specifically biostatistics, become increasingly complex, conventional tabular and graphical formats may not effectively convey the intricate patterns and relationships within the data (Abdulla et al., 2021). Therefore, this chapter covers some advanced graphical techniques that provide a visual context for facilitating a quicker and more intuitive understanding of complex relationships among real-world data in biostatistics and data science.

Pages: 28

To conduct advanced analyses, especially on large-scale biological data, researchers must examine the distributional characteristics of the data. Chapters 3 and 4 focused on various graphical methods to provide a preliminary understanding of the data’s distributional pattern. However, to ensure a comprehensive grasp of the distributional characteristics, researchers require quantitative measures. Hence, the objective of this chapter is to acquaint researchers, academicians, and professionals with quantitative techniques, such as measures of central tendency and dispersion. These techniques aid in quantifying the distributional characteristics of the data. Real-life examples are solved using R for a clearer understanding.

Pages: 30

Probability theory plays a key role in biostatistical inference. This chapter provides an overview of the concept of probability theory, along with real-life examples. It also discusses the understanding of the random variable and some probability distributions used in biostatistics and data science. All examples are explained along with the R codes.

Pages: 39

Statistical data science–based estimation and hypothesis testing are foundational tools in research and decision-making across various disciplines, including health sciences, social sciences, economics, and engineering. They enable researchers to draw inferences about population parameters, evaluate the effectiveness of interventions, and contribute to the advancement of knowledge. This chapter discusses important data science concepts and inferential techniques of statistical estimation and hypothesis testing through practical examples.

Pages: 19

The exploration of normality testing holds crucial importance in the realms of data science and biostatistics, influencing the reliability and validity of statistical analyses in these fields. It is a crucial stage devoted to exploring the distributional characteristics of data. Understanding the normality of data empowers researchers, academicians, and professionals to make informed decisions about the appropriateness of various statistical analyses and to interpret their results accurately. This chapter serves as a guide to determine the answer to the fundamental question of whether a dataset follows the bell-shaped (symmetric) curve of a normal distribution, a fundamental assumption that is required for many statistical methods. This chapter is navigated to the aspects of the normality of data, why it is so important, and different graphical and frequentist approaches for testing the normality of real-life data.

Pages: 19

Nonparametric tests, also known as distribution-free tests, are statistical tests used in hypothesis testing when certain assumptions about the population distribution, such as normality, are not met. These tests do not rely on specific population parameters (hence the term ‘nonparametric’) and are used when dealing with ordinal, nominal, or non-normally distributed data. The flexibility and robustness of nonparametric tests make them indispensable in biostatistics, allowing researchers and healthcare professionals to draw meaningful conclusions from data that may not adhere to the stringent assumptions of parametric methods. Therefore, in this chapter, different nonparametric tests are discussed with their applications. Moreover, the relevant R-code and output are presented for contemporary biostatistical applications with cutting-edge data.

Pages: 25

In the domain of data science and biostatistics, the concept of the ‘Statistical Association’ stands as a fundamental and powerful tool for scientific analysis and statistical inference. Statistical association allows us to describe the relationships between variables and make informed predictions and decisions based on these relationships. This chapter covers nuances of statistical association, its significance, and the techniques used to uncover, quantify, and interpret the connection between variables, ultimately enhancing the ability of the researcher to draw meaningful insights from data, with a specific focus on biostatistics applications.

Pages: 66

In data analysis, understanding the relationships between variables is a fundamental task. In Chapter 10, we discussed correlation, which does not cover all aspects of relationships between variables in data. This chapter comprehensively explores a powerful statistical technique, ‘regression analysis’, widely employed for modeling relationships between variables. Regression analysis enables researchers to model, predict, and understand the complex relationships between the dependent and independent variables, providing a quantitative framework to understand the nature and strength of these associations. Whether predicting future outcomes, testing hypotheses, or gaining insights into the overall pattern of the data, regression analysis offers a versatile technique. This chapter investigates the fundamentals of regression, encompassing various types with appropriate applications, each tailored to address specific data structures and research questions. Therefore, the chapter aims to equip readers with a robust understanding of regression analysis with applications targeted at biological sciences, including biostatistical and public health datasets, with real-life problem-solving using R-programming.

Pages: 23

This chapter covers two important techniques that help contemporary researchers, including biostatisticians and data scientists for decision-making.