Scientists today collect samples of curves and other functional observations. This monograph presents various ideas and techniques for analyzing such data. It includes expressions in the functional domain of linear regression, principal components analysis, linear modeling, and canonical correlation analysis, alongside specific functional techniques like curve registration and principal differential analysis. Real application data are used throughout for motivation and illustration, demonstrating how functional approaches reveal new insights by leveraging the smoothness of the processes generating the data. The data sets exemplify the broad scope of functional data analysis, drawn from fields such as growth analysis, meteorology, biomechanics, equine science, economics, and medicine. The book introduces novel statistical technology while maintaining a widely accessible mathematical level, appealing to students, applied data analysts, and experienced researchers. Much of the content is based on the authors' own work, with some material presented for the first time. Jim Ramsay, an authority on multivariate analysis, illustrates his contributions through collaborations in various fields. Bernard Silverman, known for his work on smoothing methods, adds depth to the discussion of applied statistics.
