Ebook A Student&rsquos Guide to Bayesian Statistics Ben Lambert Books
Ebook A Student&rsquos Guide to Bayesian Statistics Ben Lambert Books
Download As PDF : A Student&rsquos Guide to Bayesian Statistics Ben Lambert Books
Supported by a wealth of learning features, exercises, and visual elements as well as online video tutorials and interactive simulations, this book is the first student-focused introduction to Bayesian statistics.
Without sacrificing technical integrity for the sake of simplicity, the author draws upon accessible, student-friendly language to provide approachable instruction perfectly aimed at statistics and Bayesian newcomers. Through a logical structure that introduces and builds upon key concepts in a gradual way and slowly acclimatizes students to using R and Stan software, the book covers
- An introduction to probability and Bayesian inference
- Understanding Bayes′ ruleÂ
- Nuts and bolts of Bayesian analytic methods
- Computational Bayes and real-world Bayesian analysis
- Regression analysis and hierarchical methods
This unique guide will help students develop the statistical confidence and skills to put the Bayesian formula into practice, from the basic concepts of statistical inference to complex applications of analyses.
Ebook A Student&rsquos Guide to Bayesian Statistics Ben Lambert Books
"KINDLE VS. PAPER:
First, if you're going to buy this book, DO NOT buy the kindle version as I did. As is commonly the case with kindle versions, some of the larger graphics do not come out well (they're unreadable) and the flow of the book doesn't make much sense given how much you have to jump around from text to images and back (and zoom in and out) in the digital version. It's a humongous headache so get the textbook instead.
PROMISED RESOURCES:
Second, be aware that the website with the promised interactive resources, videos, exercises, etc... is still not up. See the author's comment below for info on how to get the solutions to the exercises. Furthermore, you can find the Youtube videos the book references (albeit with some videos missing either due to improper order, different names, or otherwise) by searching for the author's channel. The promised interactive simulations/resources? I have no idea where those are.
Long story short, the book's promised resources are, at best, disorganized and some are completely missing in whole or in part.
Clearly this is the publisher's hiccup.
WHAT YOU WILL (NOT) LEARN:
As for the book itself, it is definitely good and much better than most alternatives I've come across on the topic but don't expect miracles either.
What's good?
1. Anyone who has 0 or minimal knowledge of Bayesian concepts will learn a lot from this book about the basic/fundamental/theoretical concepts about Bayesian stats. This book is probably the best at explaining the basics, next to Open University's now out of print text.
2. This is a great reference book for those who want a quick cheat sheet on what priors and likelihoods to use for their data. I've never come across any book that organizes all of this information and explains it so well.
What's not good?
1. Many concepts and terms are presented in an illogical order such that you will have to read the entire text and then re-read numerous parts again to truly make sense of what was being said the first time around. If you're ok with reading the book 2-3 times to clarify things that aren't explained well in order, then you might enjoy this book. If you are looking for a book that clearly explains everything in logical order before moving on to a new term or concept in the hopes of only working through the book once, this isn't for you.
2. Practical application. This book falls far short of any practical use. The examples used are often simple coin toss examples, not real world ones alhough this might be good for a basic understanding of concepts for some people, of course.
3. Coding. This book is horrendous at explaining how to move from theory/math into practical/useful coding. All of the sections on coding are very poorly explained and you should have a good grasp of R/Stan before delving in if you're going to get anything out of it.
Final note: what this book, like so many on Bayesian stats, fails to do is clearly explained the advanced topics. Most Bayesian authors, like Lambert, start strong at clearly explaining basic concepts but then (perhaps tired of writing the later parts of the book thereafter) start to write in a manner that doesn't explain the more advanced topics nearly as well as the beginner sections.
Where to go from here? Check out McElreath's book on the topic for a more practical approach (although Ben does a better job of laying the foundations than McElreath in some respects)."
Product details
|
Tags : A Student’s Guide to Bayesian Statistics (9781473916364) Ben Lambert Books,Ben Lambert,A Student’s Guide to Bayesian Statistics,SAGE Publications Ltd,1473916364,Bayesian statistical decision theory,Bayesian Statistics; Bayesian Analysis; Bayesian Analytics; Bayesian Data analysis; Bayesian theory,Bayesian Statistics;Bayesian Analysis;Bayesian Analytics;Bayesian Data analysis;Bayesian theory;Bayesian Statistics introduction;Bayesian introduction;Analysis Bayesian;Bayesian methods,Great Britain/British Isles,MATHEMATICS / Probability Statistics / Bayesian Analysis,Methodology,Non-Fiction,Research,Research methods general,SOCIAL SCIENCE,SOCIAL SCIENCE / Methodology,SOCIAL SCIENCE / Research,Scholarly/Graduate,Sociology,TEXT,Textbooks (Various Levels)
A Student&rsquos Guide to Bayesian Statistics Ben Lambert Books Reviews :
A Student&rsquos Guide to Bayesian Statistics Ben Lambert Books Reviews
- I am a fan of Ben Lambert's highly intuitive videos of various Econometric topics on YouTube, so naturally I thought the style would extend to his textbook. I was mistaken. The book is poorly organized, with explanations jumping all around and not enough detail to connect theory to applications. The latter, though the author emphasizes his fondness for them, are infrequent and only half explained. Videos to supplement the text, which the author makes available online, are incomplete for latter chapters at the time of this writing.
Furthermore, and most crucially, the problem sets which the author posits as a means for applying the techniques he discusses in the previous chapter, are in almost every circumstance totally divorced from the skills outlined in the chapter they supposedly reflect. It's as if Lambert wrote the textbook for an introductory audience and the problem sets for his graduate students. Many, if not most, of the applied exercises assume at least an intermediate to advanced knowledge of both R and Stan (and Mathematica, to boot). Most of the exercises also broach statistical topics not addressed whatsoever in the previous chapter. It's as if the author is showing off his research skills to his audience rather than engaging their knowledge of chapter contents in an effective applied context. This is a real shame, and seems to be endemic in most Bayes texts, particularly Gelman, who Lambert cites endlessly throughout the work. Notable exceptions of John Krushcke's "Doing Bayesian Data Analysis" and Richard McElreath's "Statistical Rethinking," both of which I recommend over this book. Both McElreath and Kruschke do what Lambert fails to do link Bayesian concept to data analysis in an understandable applied setting. - This is the best attempt to go from 0 to 60 and beyond with Bayesian Statistics. Assumes minimal background, illustrates key points clearly and "comes with" a youtube playlist elaborating on the tricky points. Unfortunately the publisher seems to have dropped the ball on some additional extras, but what's included is already awesome.
- KINDLE VS. PAPER
First, if you're going to buy this book, DO NOT buy the kindle version as I did. As is commonly the case with kindle versions, some of the larger graphics do not come out well (they're unreadable) and the flow of the book doesn't make much sense given how much you have to jump around from text to images and back (and zoom in and out) in the digital version. It's a humongous headache so get the textbook instead.
PROMISED RESOURCES
Second, be aware that the website with the promised interactive resources, videos, exercises, etc... is still not up. See the author's comment below for info on how to get the solutions to the exercises. Furthermore, you can find the Youtube videos the book references (albeit with some videos missing either due to improper order, different names, or otherwise) by searching for the author's channel. The promised interactive simulations/resources? I have no idea where those are.
Long story short, the book's promised resources are, at best, disorganized and some are completely missing in whole or in part.
Clearly this is the publisher's hiccup.
WHAT YOU WILL (NOT) LEARN
As for the book itself, it is definitely good and much better than most alternatives I've come across on the topic but don't expect miracles either.
What's good?
1. Anyone who has 0 or minimal knowledge of Bayesian concepts will learn a lot from this book about the basic/fundamental/theoretical concepts about Bayesian stats. This book is probably the best at explaining the basics, next to Open University's now out of print text.
2. This is a great reference book for those who want a quick cheat sheet on what priors and likelihoods to use for their data. I've never come across any book that organizes all of this information and explains it so well.
What's not good?
1. Many concepts and terms are presented in an illogical order such that you will have to read the entire text and then re-read numerous parts again to truly make sense of what was being said the first time around. If you're ok with reading the book 2-3 times to clarify things that aren't explained well in order, then you might enjoy this book. If you are looking for a book that clearly explains everything in logical order before moving on to a new term or concept in the hopes of only working through the book once, this isn't for you.
2. Practical application. This book falls far short of any practical use. The examples used are often simple coin toss examples, not real world ones alhough this might be good for a basic understanding of concepts for some people, of course.
3. Coding. This book is horrendous at explaining how to move from theory/math into practical/useful coding. All of the sections on coding are very poorly explained and you should have a good grasp of R/Stan before delving in if you're going to get anything out of it.
Final note what this book, like so many on Bayesian stats, fails to do is clearly explained the advanced topics. Most Bayesian authors, like Lambert, start strong at clearly explaining basic concepts but then (perhaps tired of writing the later parts of the book thereafter) start to write in a manner that doesn't explain the more advanced topics nearly as well as the beginner sections.
Where to go from here? Check out McElreath's book on the topic for a more practical approach (although Ben does a better job of laying the foundations than McElreath in some respects). - I accidentally saw this book on and was immediately attracted by the name of each chapter and section in this book; after I bought this book, I was impressed by the real contents in this book while reading. With little math in the book, the author is presenting bayesian statistics conceptually which is awesome and even more difficult than just listing tons of mathematical equations and probability density functions. Even best, there are problem sets at the end of each chapter and online videos and answers to the problems sets for you to learn, practice, and learn again!
- This is the Bayes book I've been waiting for.... Thank you
- I think it is a very basic and interesting book not only for math or science students but for anybody with some notions of probabilities. I feel that maybe more examples and tools to see numerical results could be an asset for the book. However, I do recommend it!!
- Rare book with such in-depth discussion of priors, likelihoods and posteriors
- One of the absolute best introductions to Bayesian statistics that I have seen
Comments
Post a Comment