Statistical Practice for Data Science: with Hands-on Illustrations using R is a comprehensive guide designed to equip students from diverse fields—engineering, science, and the biological, physical, and social sciences—with the statistical tools and techniques essential for data science. This book bridges the gap between theoretical concepts and practical applications, offering a clear and accessible introduction to statistics with minimal mathematical prerequisites. With a focus on real-world datasets and hands-on implementation using R, it empowers students to analyze, interpret, and communicate data effectively.
The book begins with foundational concepts in probability and statistics, ensuring that students with only college-level algebra can grasp the material. It progresses through key topics such as data visualization, hypothesis testing, regression modeling, and modern machine learning methods like random forests and gradient boosting. Each chapter is enriched with practical examples and coding exercises in R, making it an invaluable resource for students embarking on a data science program.
Designed as a one-semester course, the book provides flexibility for instructors to tailor the content to their curriculum. Whether exploring generalized linear models, mixed-effects models, or dependent data analysis, students will gain a deep understanding of statistical methods and their applications across various domains. By the end of the book, readers will be equipped to make informed decisions, quantify uncertainty, and communicate their findings effectively.
This book is not just a learning tool—it’s a practical companion for aspiring data scientists seeking to master statistical practice and R programming.
Table of Contents:
1. Useful Preliminaries 2. Data Visualization 3. Two Sample Inference 4. Fixed Effects Analysis of Variance Models 5. Linear Regression Analysis 6. Linear Regression – More Topics 7. Generalized Linear Models (GLIM) 8. More on GLIM and Related Methods 9. Some Extensions to ANOVA Models 10. Models for Dependent Data
About the Author :
Nalini Ravishanker is Professor in the Department of Statistics at the University of Connecticut (UConn), Storrs. She has a PhD in Statistics and Operations Research from the Stern School of Business, New York University, and a B.Sc. in Statistics from Presidency College, Madras, India. Her primary area of research is time series analysis with applications in several domains.
G. Asha is Senior Professor in the Department of Statistics at Cochin University of Science and Technology, Cochin, Kerala, India. She has a MPhil in Statistics from University of Kerala and Ph D in Statistics from Cochin University of Science and Technology, Cochin. Her primary area of research is life time data analysis.
Haim Bar Professor in the Department of Statistics at the University of Connecticut (UConn), Storrs. He has a PhD in Statistics from Cornell University, MSc in Computer Science from Yale University, and BSc in Mathematics from the Hebrew University. His areas of interest include high-dimensional models, and applications in genomics.
