In this book, we give many synthetic and real data examples to demonstrate that conventional methods are not optimal and how accuracy improves if truly optimal methods are employed. However, computing optimal estimates alone is not sufficient; at the same time, we must evaluate in quantitative terms how reliable the resulting estimates are. The knowledge that a distance is optimally estimated to be 5m is of little use if we do not know whether the value is reliable within ±10cm or ±lm. This reliability issue has not received much attention in the past. In order to compute optimal estimates and evaluate their reliability, we need an efficient numerical algorithm. Since such estimation is based on our knowledge about the structure of the problem, we also need a criterion for testing if the assumed structure, or model, is correct. This book presents rigorous mathematical techniques for these purposes.