I was wondering if there was a document or a website that shows how statsitical techniques relate to each other and when to use each of them. I'm an engineer and every time I need to use a certain model (for bayesian inference for example), I have to go throw a lot of papers and websites to find what really applies to my problem. Should I use Conditional random fields, Deep Gaussian processes, recursive bayesian models, ... ?
A statistician might know his way around these techniques and instantly know what to use, but I don't seem to find a book or a website that translates the "math" in simpler terms, something like : if you have this stuation, you should use this model (don't get me wrong I love a good model and I'm ready to go through its details if necessary), but for someone who has basic understanding of PCA, factor analysis and LDA, going through methods like CRF, GP, HMM, .. without knowing if it's really what's you're looking for can be really tiring ..
So back to my question, I would like to know if there was some kind of "taxonomy" of statistical tools (something like this (http://amueller.github.io/sklearn_tutorial/cheat_sheet.png)) but for statistical analysis, inference and bayesian models not for machine learning.
Any suggestion is much appreciated. Thanks for all of you !
