Note that the first sentence of the linked page says that:
> This is a draft textbook on data analysis methods, intended for a one-semester course for advance undergraduate students who have already taken classes in probability, mathematical statistics, and linear regression.
> The mathematical level of these notes is deliberately low; nothing should be beyond a competent third-year undergraduate. But every subject covered here can be profitably studied using vastly more sophisticated techniques; that’s why this is advanced data analysis from an elementary point of view.
"Elementary" is a relative term in my experience.
The formula on 29 is the expected value of the quantity, (Y-m)^2. It is the average squared error under the distribution of Y incurred by a chosen value of m.
You could probably get a phd in math using only textbooks with some variation of "introductory" in the title, so when dealing with math textbooks I recommend ignoring any words that normal people would interpret as indicating a certain level of difficulty.
This book is a great resource. I've gone back to it frequently. If you're interested in getting into statistics and machine learning, I cannot recommend this book highly enough. The motivations are good, and the explanations are good. Shalizi's class for this book at CMU is highly sought after, and some of that surely makes its way into this massive book.
I took 36-402 with Shalizi during my final semester at CMU and liked it a lot. (although the homework certainly took awhile!)
Notably, it used just as much coding in R as statistical theory, which was good for me since I was a coder, and less good for the majority of the class. :P
Before taking this class I didn't know cross validation, bootstrapping or about double dipping data. I think those are the most important takeaways. The discussion of causality and building graphical models was good as well.
8 comments
[ 4.0 ms ] story [ 33.0 ms ] threadThe first formula (regression on page 29) instantly drops some math in there without any discussion of what it does or how it got there... :(
> This is a draft textbook on data analysis methods, intended for a one-semester course for advance undergraduate students who have already taken classes in probability, mathematical statistics, and linear regression.
> The mathematical level of these notes is deliberately low; nothing should be beyond a competent third-year undergraduate. But every subject covered here can be profitably studied using vastly more sophisticated techniques; that’s why this is advanced data analysis from an elementary point of view.
"Elementary" is a relative term in my experience.
The formula on 29 is the expected value of the quantity, (Y-m)^2. It is the average squared error under the distribution of Y incurred by a chosen value of m.
Notably, it used just as much coding in R as statistical theory, which was good for me since I was a coder, and less good for the majority of the class. :P