Название: Data Analysis : A Gentle Introduction for Future Data Scientists
Автор: Graham Upton, Dan Brawn
Издательство: Oxford University Press
Год: 2023
Страниц: 161
Язык: английский
Формат: pdf (true)
Размер: 10.2 MB

Data analysis has been a hot topic for a number of years, and many future data scientists have backgrounds that are relatively light in mathematics. This slim volume provides a very approachable guide to the techniques of the subject, designed with such people in mind. Formulae are kept to a minimum, but the book's scope is broad, introducing the basic ideas of probability and statistics and more advanced techniques such as generalised linear models, classification using logistic regression, and support-vector machines.

An essential feature of the book is that it does not tie to any particular software. The methods introduced in this book could also be implemented using any other statistical software and applying any major statistical package. Academically, the book amounts to a first course, practical for those at the undergraduate level, either as part of a mathematics/statistics degree or as a data-oriented option for a non-mathematics degree.

This book aims to provide the would-be data scientist with a working idea of the most frequently used tools of data analysis. Our aim has been to introduce approaches to data analysis with a minimum of equations.

We envisage three general classes of readers: the complete novice, those with existing statistical knowledge, and those currently employed as data scientists or using Data Science who wish to widen their repertoire and learn something of the underlying methodology.

The entire book is relevant for the novice. The earlier chapters may be most relevant for the practitioner, since they provide the background to the methods used in later chapters, while for statisticians new to data science it will be the final chapters that are of most use.

As a data scientist you will be using the computer to perform the data analysis. Any programming language should be able to carry out the analyses that we describe. We used R (because it is free); our code is available as an accompaniment to the book.

The book appeals to would-be data scientists who may be formula shy. However, it could also be a relevant purchase for statisticians and mathematicians, for whom data science is a new departure, overall appealing to any computer-literate reader with data to analyse.