This page was created to share some of the educational resources I personally used or consulted as an integration to my studies and that I would probably suggest. My background was not even close to mathematics (I even did a classical lyceum in high school), but since I moved to study genetics and complex traits, I had to integrate more and more. Self-learning has become a pivotal part of my career, at this point, so I thought something like this would help other people willing to learn. If you want to enable my bad habit of hoarding self-learning sources, or you think there’s one that addresses some topics better, feel free to get in touch.
The resources are categorised by topics, in no particular order. I am trying to stick to one or two (heavily opinionated) sentence for the description, in order to make it as much concise as possible. Most of them are agnostical in terms of background, wherever possible.
The ones marked with an asterisk (
*) are usually the ones that I like to consult as a primer on topics I do not know about, or that gives enough context to be able to move on to other, more advanced resources. Some of them have a “from zero to hero” approach, some other just deal with the basics very very well. I am trying to post the free versions wherever possible, but Google is really your friend.
I also won’t stress enough that everything here is strictly in my own opinion: there are some oddballs, that I added because I think they’re useful as informal introductions, but I am not sure if they are suited for more formal contexts.
Khan Academy*: Admittedly, one of my favourite ones about general maths and basic concepts. It does one thing (providing basic education, free for everyone) and it does it well.
3Blue1Brown*: an amazing channel focusing on a thorough mathematical explanation of (usually) single, self-contained concepts–or very short series.
StatsQuest*: major complex of statistics (and related subjects) explained easily, with a minimal knowledge of basic mathematics.
The elements of statistical learning: Must-read for anyone interested in statistical learning/machine learning. Given the modular structure of this book, I’d say it is best used as a consultation resource on many topics. The only caveat is that isn’t the most entry level resource for the topic, but it has an excellent companion in An introduction to statistical learning with applications on R (here for the excellent MOOC). NOTE: ITSL would probably deserve a separate entry, but I am still finishing a couple of chapters myself.
Biostatistics for Biomedical Research: A godsend, by the author of some of the most widely used packages for statistical analysis on R (Hmisc, rms), one of the must-have books about regression (Regression Modeling Strategies) AND ALL THE RESOURCES ARE FREE. All of them. It’s the closest thing I have seen to a stats course in a top-tier university–and it surpasses all of them anyway in sheer terms of value for money. Probably the one resource this page is worth for.
Mendelian Randomization webinar by George Davey Smith: A brief webinar by one of the main developers of the method (probably the main one), with a good companion thread on Twitter. I had a couple of weeks during my MSc when I wasn’t able to understand what the hell MR was and this greatly helped.
Shenzen I/O: I haven’t found a single resource that let you practice basic concepts of programming (on electronic circuits) as well as this one. Starting with this assembly-like code make things easier with higher level programming, and it basically teaches you implicitly how coding works on a lower level.
R in Action: The book I learnt from the most. It teaches you R works first in a crystal clear way (which is the biggest perk of the book, and something I haven’t found on most of the commonly suggested ones), then how to do stats with it, in an increasingly complex order. A good complimentary book to the more renowed R4DS (cited below) to have a 360° vision of it. NOTE: I am linking the 3rd (upcoming and available in early access, as of Apr 2020) edition of the book, because the 2nd is slightly outdated on some topics, especially for Tidyverse-related packages. Nothing too bad, but I am sure the next edition will fix that. Almost all the content of the book still applies.
R for Data Science: If you haven’t heard of this resource yet, you probably need it.
What they forgot to teach you about R: The book we R self-learners always needed without knowing. A must-read after your basis is rock solid.
Have I mentioned I use a lot of Emacs? No? Well, here are some resources about it anyway:
M-x emacs-tutorial. The GNU tour is good too.
Emacs tutorial by Xah: Thorough tutorial. Probably all you will ever need (and slightly more) if you just started. Useful as a consultation resource.
Org-mode tutorial: One of the longest running videotutorials on the hardest package to learn on Emacs (the documentation for org-mode is huge and dispersive, at times, due to the amount of functions it has). It goes slow and deals with one thing at a time, which probably is the best way of learning it.
I added a small privacy section here, since it might be useful in case you deal with sensitive data or other kind of private informations.