'This is an enormous book, covering in extraordinary detail all the topics selected by these respected authors. It represents a substantial update and renewal of the material covered in the first edition. In my opinion it should be on the shelves of anyone dealing with discrete choice models.' Juan de Dios Ortúzar Salas, Pontificia Universidad Católica de Chile 'Choice modelling is a very active and rapidly evolving field, with applications across numerous disciplines. The first edition of Applied Choice Analysis accomplished the major task of making the breadth of work accessible to a wide audience, with hands on examples provided throughout. Nine years on, the field has developed further, and David A. Hensher, John M. Rose and William H. Greene have again performed a remarkable job in explaining these new methods without unnecessary jargon and complexity, helping to educate the next generation of choice modellers and striking exactly the right balance between theory and practice.' Stephane Hess, University of Leeds 'The new edition of this already very popular book provides substantial added value to readers. Applied choice analysis has now been extended to include all recent developments. More intuition and further clarifications have been added. The examples provided cover thoroughly the range of case study applications. This book will work perfectly as a step-by-step introduction for the neophite as well as a core reference for the practitioner. The authors have managed to strike the right balance between practicality and accuracy, without subtracting much of the econometric details.' Riccardo Scarpa, Gibson Chair for MayFood, Rural and Environmental Economics, Queens University Belfast 'I cannot imagine a better introduction to choice modeling. The authors manage to bring a vivid, storytelling voice to this complex topic, with language that has personality and rhythm. The various interrelated concepts and procedures that constitute choice modeling come across as simple and straightforward. An amazing feat. The ins-and-outs of a computer code are also taught along with the statistical methods. This integration of computer language within the text is unusual and highly valuable, giving readers all the steps that are needed to implement the methods on their own data.' Kenneth Train, Adjunct Professor, University of California, Berkeley