Practical Statistics for Data Scientists: 50 Essential Concepts 1st Edition

There's always that one person who is unsatisfied, but it sure as hell isn't me, because I knew what this book was going to be like the moment I saw how many pages it was going to have & how the early release version looked. I still preordered a hard copy (for sharing) & a digital copy (for carrying), because I knew this was kind of what type of book I was looking for & then some.The concepts are not astronomically explained, but with just enough depth that I can also individually explain to people what they are. What really stands out for me so far is after each or so concept, there is a section labeled as further reading (well, in the digital copy) that is usually at the end of the book altogether & I found myself realizing I have a lot of those books so the authors really know where to look & guide those who wanted more depth.Yeah yeah yeah, the codes are missing (as of mid-June 2017) but if you really understood / know which packages to use, you wouldn't need the code. The first half of the book are two three liners of code concepts anyways; it's the explanations that matter the most. The second half of the book is the good part, which separates a white hat statistician from a grey hat data scientist, which is exactly what I wanted in a <300 page book.Thanks for keeping me waiting since November though, thought it would never come! The O`Reilly books always keep me in awe at how they always know what topic I want to have a brief book (probably data collecting on me :P) & simultaneously leave me in suspense because I never notice I am preordering the books! Sigh. My only request is to be able to preorder the Kindle editions rather than the physical editions; my data science book cubby is starting to overwhelm my statistics cubby (NOT FOR LONG MASTERS PROGRAM ~).

Information seems plainly written and relevant. No link to datasets makes the "practical" code portion of the book unusable. Will happily update my review when the datasets are released.EDIT:Ok the datasets are up. There is a short R script to run to download the data, it will require some small modifications to get it working correctly.You need to create a folder named "data".and I changed the second line in the script from:PSDS_PATH <- file.path('~', 'statistics-for-data-scientists')to this:PSDS_PATH <- file.path('.')This will download the data into a folder named "data" in whatever directory you run the script. The script runs with no real feedback and some of the data sets are large, so just be patient. Once these were downloaded the examples in the book run great.

First of all, this book is not for you if you want a deep and thorough explanation of statistical concepts. It serves a completely different purpose: to familiarize a reader with high-level concepts; to enable them to continue their statistics education elsewhere.I found this book a very engaging read: it sets itself apart from other books on statistics in clearly telling which concepts are not-so-relevant for the modern computerized explorative analysis toolset. Many concepts that are presented in classic books on the subjects are rooted in 20s and 30s where computing power wasn't available and researches resorted to various pre-calculated distributions and formulas to do their work. A modern data-scientist's approach would eschew some of the old ways and instead rely on randomization, resampling and computing power.This book not only tells what something is, but also why it is that way and if a concept is still relevant today.I can recommend this book if your statistics knowledge is spotty or ephemeral, it serves its purpose well and doesn't bog down the reader with (sometimes) unnecessary mathematical concepts to demonstrate an idea.Why the four stars:1. Lack of examples in programming languages.2. Complete lack of exercises (at least 1-2 exercises are necessary).3. All scarce examples that are available are in R. No Python. :(

Excellent introductory text for a comprehensive overview of statistics! The github repository augments the content very well and provides added value for the statistical topics covered in the book. Both of the Bruce brothers are statistical gurus and this fact is evident in the writing, which is both informative and witty. Peter is the president of Statistics.com and is well-versed in providing statistical instruction to students of all ages and levels. He is also a proponent of resampling and one of the developers of the excellent Resampling Stats software package for Excel.It is true that the textbook does not provide in-depth coverage for all topics, but I don't think that was the intent of the authors. However, the text DOES provide an excellent introduction to topics relevant to students and data scientists. After reading the text and working through the examples, you will be equipped to further your knowledge in whichever topic you require for you data analysis task.Highly recommended!

I bought this book for $13 an it has been a great read. Numerous major concepts required for a data scientist interview have been covered in this book. If you ask me, it's worth every cent spent on it. I gifted a second one to my friend who is in a Data Science program.