Parametric and Nonparametric Inference for Statistical Dynamic Shape Analysis with Applications

The book "Parametric and Nonparametric Inference for Statistical Dynamic Shape Analysis with Applications" offers a comprehensive examination of specific inferential questions arising from the analysis of dynamic shapes. It aims to address these challenges through the use of probability models and nonparametric tests. The models presented are easy to understand and interpret, making them a useful tool for describing the global dynamics of landmark configurations. However, due to the non-Euclidean nature of shape spaces, determining distributions in these spaces is not trivial. The book discusses the application of the Gaussian distribution in configuration space and integrates similarity transformations. It provides a solid foundation for statistical inference based on temporal sequences of landmark configurations and enables the derivation of inference for Gaussian processes in shape space. The structure of the book is divided into two parts, with the first three chapters addressing the offset-normal shape distribution and the remaining chapters covering the theory of nonparametric combination tests. The chapters include a collection of applications linked by the central theme of the book.