-
PDF
- Split View
-
Views
-
Cite
Cite
Massimiliano Caporin, Statistical Analysis of Financial Data: with Examples in R, Journal of the Royal Statistical Society Series A: Statistics in Society, Volume 185, Issue 1, January 2022, Pages 432–433, https://doi.org/10.1111/rssa.12764
Close - Share Icon Share
When writing a book dedicated to the use of statistical tools within a specific field, the author tackles a challenging mixture of three objectives: to find an appropriate compromise between distilling rigorous statistical concepts, appropriately introduce the readers to the framework where the tools will be applied and provide insightful examples. I believe this book greatly succeeds in two of these objectives.
The first chapter is a long introduction condensing concepts, elements and actors, referring to financial markets functioning and financial data creation. As the author clearly states, no prior knowledge in finance is required, and thus this chapter gives the background to readers interested in financial data with some minimal knowledge in mathematics and statistics. I particularly appreciate the introduction to finance as a medium to review some basic concepts in statistics, and the presence of a detailed introduction to the R software, fundamental to replicate the book’s examples. The second and third chapters focus on exploratory data analysis, with a review of graphical tools, of further statistical concepts, and unconditional probability distributions, touching discrete and continuous, univariate and multivariate densities; as a statistician, I really appreciate the clarity of these two chapters, but if I were interested in financial data analysis, I would miss examples helping in contextualizing the tools into realistic finance world case studies. Chapter 4 is a great review of statistical models, estimation and inferential methods, with some examples focusing on financial applications. The chapter is really dense, but provides an overview on a number of methods that are currently applied in the financial data analysis field, starting from the linear model up to simulation-based methods, value-at-risk and expected shortfall estimation, up to the joint analysis of several variables. The last chapter is a condensate of time series methods for finance with some application. Despite I appreciate the effort of providing a concise summary of the most relevant approaches for the analysis of financial time series, I believe these tools, in particular GARCH models and the use of dynamic models for the forecast of risk or other risk-related indicators, among the most relevant elements for financial data analyses, should have deserved a much larger space. Moving from ARMA models to GARCH and cointegration into a single chapter might be too much for readers without any prior knowledge of time series analysis.
Overall, I believe the book is perfect for readers with limited statistical and financial knowledge interested in having a first look both at financial data creation and at the statistical methods that could be used to analyse financial data; traders and financial analysts would suffer for the limited real-life examples, but they will benefit for the extensive and detailed introduction to the statistical tools for financial data analysis.