I am looking for theoretical resources (books, tutorials, etc.) to learn about making sound statistical inferences given (plenty of) multivariate website conversion data.
I'm after the math involved, and cannot find any good non-marketing stuff on the web. The sort of questions I want to answer: how much impact does a single variable (e.g. color of text) have? what is the correlation between variables? what type of distribution is used for modelling (Gaussian, Binomial, etc.)? When using statistics to analyze results - what should be considered as a random variable - the web-page element that gets different variations or the binary conversion-or-no-conversion outcome of an impression?
There's plenty of information about different website optimization testing methods and their benefits\pitfalls, plenty of information about multivariate statistics in general, do you guys know of resources that discuss statistics in this specific context of website optimization?