The Book to learn Statistics for Data Scientists

Ever wondered how to learn the necessary statistics for data science, while escaping from the boring, theoretical books? Read on to find how!

Review of Practical Statistics for Data Scientist

The second edition was published in 2020 and includes both R and Python examples. This review discusses that edition; check the edition on the cover before buying or following a code example.

If you are familiar with R or Python (this second programming language is only included in the second edition), and have had some previous exposure to statistics, this concise book will get you up and running with complex statistical methods, experiments and procedures in these two programming languages. If you are new to programming, you can find some very good reviews of Python books here.

The book can strengthen your statistical judgment, but reading alone will not make you an expert. Reproduce examples, explain assumptions, and practise choosing a method for a new question.

This book is more oriented towards programmers that have some statistics knowledge than to data scientists who are probably very familiar with these topics. If you are a programmer that wants to approach data science, or a Data Scientist with a lack of statistical knowledge, then this book is a very good buy for you.

In a world full of statistics post, threads on stack overflow, and books, Practical Statistics for Data Scientist can serve as a reference manual to have near by and look up in case you need to refresh an old concept or look at how to implement something precisely.

Overall a great read and a fantastic reference manual for punctual questions.

Book description and contents

This book is aimed at the data scientist with some familiarity with the R and/or Python programming languages, and with some prior (perhaps spotty or ephemeral) exposure to statistics. Two of the authors came to the world of data science from the world of statistics, and have some appreciation of the contribution that statistics can make to the art of data science.

Its focus is applied statistical reasoning: sampling, uncertainty, experiments, regression, and related methods. Use a separate deep-learning resource if neural networks are your main goal.

The second edition includes examples in R and Python. Use the official companion repository for code and datasets, and follow the setup instructions for your chosen language.

Two goals underlie this book:

• To lay out, in digestible, navigable, and easily referenced form, key concepts from statistics that are relevant to data science.
• To explain which concepts are important and useful from a data science perspective, which are less so, and why.

The publisher’s second-edition page provides the contents. Match it with the second-edition companion code; the first edition primarily used R.

About the book: Practical Statistics for Data Scientist

Authors

Peter Bruce is the Founder and Chief Academic Officer of the Institute for Statistics Education at Statistics.com, which offers about 80 courses in statistics and analytics, roughly half of which are aimed at data scientists. He has authored or co-authored several books in statistics and analytics, and he earned his Bachelor’s degree at Princeton, and Masters degrees at Harvard and the University of Maryland.

Andrew Bruce, Principal Research Scientist at Amazon, has over 30 years of experience in statistics and data science in academia, government and business. The co-author of Applied Wavelet Analysis with S-PLUS, he earned his bachelor’s degree at Princeton, and PhD in statistics at the University of Washington

Peter Gedeck, Senior Data Scientist at Collaborative Drug Discovery, specializes in the development of machine learning algorithms to predict biological and physicochemical properties of drug candidates. Co-author of Data Mining for Business Analytics, he earned PhD’s in Chemistry from the University of Erlangen-Nürnberg in Germany and Mathematics from Fernuniversität Hagen, Germany

Pages: 368

Publications: First publication 2017, Second publication 2020

Summary of Practical Statistics for Data Scientist

Practical Statistics for Data Scientist is a book that is very well defined by its name: it is a very hands-on book to learn the most important statistical concepts and tools used in the data science world.

Treat this as a practical foundation and reference, not an exhaustive statistics curriculum. Return to the relevant chapter when you need to assess sampling bias, uncertainty, or a modeling assumption.

With a book like this one, complemented with a Machine Learning book like “Hands-On Machine Learning with Scikit-Learn & TensorFlow”, you will be on your path to becoming an excellent Data Scientist if that is what you want.

For experts in Data Science or Machine Learning, the book can serve as a reference manual to have near by for looking up how to implement various algorithms. Overall, a good read, that we surely enjoyed. We hope you do too.

Try a small bootstrap exercise: repeatedly resample a dataset, calculate the mean each time, and inspect how variable those estimates are. Begin with exploratory data analysis so you understand missing values and unusual observations before interpreting the results.

We hope you liked the review, for more like it, check our Data Analysis Books category.

Thanks for reading How to Learn Machine Learning and have an awesome day!

Tags: Practical Statistics for Data Science, Practical Statistics for Data Scientist, Statistics and Probability, Programming, Python, Machine Learning, Statistics for Machine Learning.