Hierarchical Models and Andrew Gelman's Blog

Andrew Gelman is professor of statistics and political science at Columbia University. His book Data Analysis Using Regression and Multilevel/Hierarchical Models (with Jennifer Hill) is also quite important for empirical corporate finance. Hierarchical models are also known under the names mixed models, mixed effects models, multilevel models, random coefficients models, and variance components models.

Consider for simplicity linear models. Mixed linear models are related to what econometricians call the random effects model. The key difference is that random effects models specify only the intercept coefficient to be random. Richer models such as mixed linear models also permit the slope parameters to be random.

Professor Gelman also has a great blog where discusses many important concepts. See for example his post on how to think about instrumental variables when you get confused (and who doesn't sometimes get confused when trying to come up with good instruments). Professor Jackman has a related blog, the most interesting parts from FinanceStrudel's point of view are probably those on statistics and computing.