-
PDF
- Split View
-
Views
-
Cite
Cite
Md. Moyazzem Hossain, Statistical Regression Modeling with R, Journal of the Royal Statistical Society Series A: Statistics in Society, Volume 185, Issue 2, April 2022, Pages 743–744, https://doi.org/10.1111/rssa.12817
Close - Share Icon Share
Nowadays, different statistical techniques are widely used by researchers and practitioners for decision and policy-making purposes in different fields including social science, engineering, environmental science, health science and so on for enhancing population well-being. Among the statistical techniques, regression analysis contributes a lot for producing valid, effective, and efficient decisions analysing real-life data. However, the classical regression modelling is unable to generate the appropriate evidence for making decisions efficiently in the case of multilevel or clustered data. The authors of this book produce a great introductory as well as a useful guide to find the potential results from multilevel data.
This book consists of ten chapters. Chapter 1 gives an overview of widely used classical regression modelling, that is simple and multiple linear regression along with applications. From Chapters 2 to 4, the authors nicely presented the concept of one level to multilevel modelling including the theoretical and practical point of view along with R code, output and their interpretations. Longitudinal data analysis including examples of real-life data is discussed in Chapter 5. The techniques of nonlinear regression are introduced in Chapter 6 with an emphasis on logistic growth modelling. In Chapter 7, the authors focused on the nonlinear multilevel regression model and how to utilize the R package ‘nlme’ to analyse an extensively used data set on loblolly pines growth. In Chapter 8, the readers learn about logistic regression applicable for categorical data, poisson regression, and negative binomial regression suitable for overdispersed counts data, as well as generalized linear regression. Moreover, Chapter 9 discusses the fitting procedure of generalized logistic regression which is suitable for multilevel categorical data using ‘lme4’ R package. The generalized linear mixed-effects model (GLMM) was explained to demonstrate how to analyse counts data having multilevel structures in Chapter 10. Finally, Appendix A lists all of the data sets utilized in the book and Appendix B discusses the R packages that were applied in this book.
For graduate students, scholars and professionals, this book is an amazing resource, a pleasant read, and an indispensable reserve. It would also, in my opinion, be an excellent inclusion to any library’s catalogue. Last of all, I wholeheartedly recommend this book to all graduate students and professionals in the related fields as a textbook as well as a reference book for research, learning and teaching.