Knowledge about inter-individual shape variations is useful for a variety of applications in orthopaedic surgery. On the one hand, it can be exploited to design surgical devices (guides or implants) that either fit a broader range of patients or are adapted to specific groups of patients (e.g. male or female).On the other hand, in a personalized therapeutic setting it helps reconstructing the patient’s anatomy in a robust and automated way from medical image data, or is used for generating patient-specific yet objective surgical reconstruction plans. Statistical shape models (SSM) are capable of capturing the variablity of anatomical shapes contained in a given population. Usually, the statistical analysis is performed on a given set of single-object training shapes (e.g. one bone/organ or a fixed compound of such structures),which are in correspondence with each other. Training instances of joint structures, such as the knee or hip, however, may exhibit different joint postures. Although one may model joint flexibility implicitly by capturing joint motion statistically (Klinder et al, MICCAI 2008; Heap et al., Image Vision Comput. 1996), this approach is beneficial only if relative transformations between individual objects are a statistical property of anatomy, which is, e.g., not the case for knee bending. Therefore, joint posture should be modeled independently by joint-specific degrees of freedoms. We are presenting so-called articulated statistical shape models (ASSM), which model statistical shape variations independently of joint postures. This allows to measure and analyse characteristic shape changes under different joint postures. We see a potential benefit both in biomechanics-based simulation studies for the optimization of surgical devices, as well as a more robust reconstruction of joint structures in medical image data, especially in the presence of low signal-to-noise ratio, pathologies or artifacts.