An introduction to analysis of financial data with R.

*(English)*Zbl 1279.91003
Wiley Series in Probability and Statistics. Hoboken, NJ: John Wiley & Sons (ISBN 978-0-470-89081-3/hbk). xiv, 390 p. (2013).

This book is thought as an introductory textbook for financial time series analysis. The idea of the author was to make the lecture as user-friendly as possible. The concepts of economic and statistical theory are presented in a simple and concise manner. The lecture focuses on practical aspects of financial data analysis. The objectives of the book expressed by the author are: to provide basic knowledge of financial time series, to introduce statistical tools for analyzing financial data, and to gain experience in financial applications. The book consists of seven chapters.

Chapter 1 presents some basic concepts dealing with financial data (asset returns, bond yields and prices, implied volatility). Next, the R program is introduced and first applications of its packages are used to present some stylized facts about financial data and ways to visualize the data.

Chapter 2 introduces basics of linear time series analysis. The importance of weak stationarity is pointed. Next the author discusses correlation and autocorrelation and the notion of linear time series. The autoregressive (AR), moving average (MA) and ARMA models are presented in detail. Some attention is paid to unit-root nonstationarity and long memory. The exponential smoothing as a method of forecasting is presented. Seasonal models and regression models with time series errors are briefly discussed. The last section of the chapter deals with model comparison and averaging.

Chapter 3 includes three case studies of linear time series. An extensive analysis of weekly regular gasoline price, global temperature anomalies and the US monthly unemployment rates is presented. This chapter is especially useful for beginners in the subject, because it shows step by step the process of modeling the data.

Chapter 4 addresses the problem of volatility measures and models. After describing the general structure of volatility models, the GARCH family is discussed quite extensively. The stochastic volatility models are mentioned. The chapter ends with information concerning the daily volatility measures based on intraday data.

Chapter 5 shows some applications of such volatility models. The presented examples include the GARCH volatility term structure, option pricing and hedging, time varying betas and minimum variance portfolios.

Chapter 6 deals with intraday data. First, some market microstructure effects and the specific properties of trading data are discussed. Next, the author presents models for price changes (ordered probit model and decomposition model) and autoregressive conditional duration (ACD models). More careful discussion on realized volatility and the methods of handling the microstructure noise from its estimates is performed.

The subject of the last, seventh, chapter of the book is value at risk (VaR). The notion of coherence of risk measures is presented with VaR and expected shortfall serving as examples of non-coherent and coherent risk measures. Next, the RiskMetrics methodology is discussed in detail. Further, the author applies volatility models to calculate VaR. Quantile regression and extreme value theory are presented as tools for VaR estimation.

Summarizing, this is an excellent textbook for an introductory but intensive course in financial econometrics, ready to use in teaching with no additional requirements and preparations. The theory is presented in simple, easy to understand way. Numerous examples illustrate well the practical aspects of financial time series analysis. The plots and demonstrations contained in the book make the modeling process and its results easy understandable. Most of the data used in the examples can be easily downloaded from open sources. The used software, the R packages, is free and works on most operating systems. Due to the combination of all these things, the book is useful if only the lecturer and students have computers and access to the internet. Even though the simplicity of the lecture, the book presents the most important topics in financial econometrics including new developments. All it makes the book extremely useful for teachers and students, and also for practitioners seeking for short path to financial data analysis and risk modeling.

Chapter 1 presents some basic concepts dealing with financial data (asset returns, bond yields and prices, implied volatility). Next, the R program is introduced and first applications of its packages are used to present some stylized facts about financial data and ways to visualize the data.

Chapter 2 introduces basics of linear time series analysis. The importance of weak stationarity is pointed. Next the author discusses correlation and autocorrelation and the notion of linear time series. The autoregressive (AR), moving average (MA) and ARMA models are presented in detail. Some attention is paid to unit-root nonstationarity and long memory. The exponential smoothing as a method of forecasting is presented. Seasonal models and regression models with time series errors are briefly discussed. The last section of the chapter deals with model comparison and averaging.

Chapter 3 includes three case studies of linear time series. An extensive analysis of weekly regular gasoline price, global temperature anomalies and the US monthly unemployment rates is presented. This chapter is especially useful for beginners in the subject, because it shows step by step the process of modeling the data.

Chapter 4 addresses the problem of volatility measures and models. After describing the general structure of volatility models, the GARCH family is discussed quite extensively. The stochastic volatility models are mentioned. The chapter ends with information concerning the daily volatility measures based on intraday data.

Chapter 5 shows some applications of such volatility models. The presented examples include the GARCH volatility term structure, option pricing and hedging, time varying betas and minimum variance portfolios.

Chapter 6 deals with intraday data. First, some market microstructure effects and the specific properties of trading data are discussed. Next, the author presents models for price changes (ordered probit model and decomposition model) and autoregressive conditional duration (ACD models). More careful discussion on realized volatility and the methods of handling the microstructure noise from its estimates is performed.

The subject of the last, seventh, chapter of the book is value at risk (VaR). The notion of coherence of risk measures is presented with VaR and expected shortfall serving as examples of non-coherent and coherent risk measures. Next, the RiskMetrics methodology is discussed in detail. Further, the author applies volatility models to calculate VaR. Quantile regression and extreme value theory are presented as tools for VaR estimation.

Summarizing, this is an excellent textbook for an introductory but intensive course in financial econometrics, ready to use in teaching with no additional requirements and preparations. The theory is presented in simple, easy to understand way. Numerous examples illustrate well the practical aspects of financial time series analysis. The plots and demonstrations contained in the book make the modeling process and its results easy understandable. Most of the data used in the examples can be easily downloaded from open sources. The used software, the R packages, is free and works on most operating systems. Due to the combination of all these things, the book is useful if only the lecturer and students have computers and access to the internet. Even though the simplicity of the lecture, the book presents the most important topics in financial econometrics including new developments. All it makes the book extremely useful for teachers and students, and also for practitioners seeking for short path to financial data analysis and risk modeling.

Reviewer: Małgorzata Doman (Poznań)

##### MSC:

91-01 | Introductory exposition (textbooks, tutorial papers, etc.) pertaining to game theory, economics, and finance |

91G70 | Statistical methods; risk measures |

91-04 | Software, source code, etc. for problems pertaining to game theory, economics, and finance |

91B84 | Economic time series analysis |

62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |

62P05 | Applications of statistics to actuarial sciences and financial mathematics |