This book explains how to analyze statistical models with hidden (latent) variables. It takes a systematic, geometric approach to studying the semialgebraic structure of latent tree models. The first part of the book introduces key concepts in algebraic statistics, focusing on methods that are helpful in the study of models with hidden variables. The second part illustrates important examples of tree models with hidden variables. The author develops the important concepts of L-cumulants and links latent tree models and various tree spaces.