In the setting of multivariate analysis, we discuss Mahalanobis' idea of a distance based on "transforming the coordinates of a statistical field". While Mahalanobis (1936) considered the set of normal distributions in particular, we will consider possible extensions to a superset of distributions. The distance can be useful for projection, as loss function, for creating acceptance regions, and for hypothesis testing. UCLA Department of Statistics 2009-10-12T15:43:06-07:00 2009-12-01 Statistics false 4:00 PM 424 4660 Geology Bldg. Uppsala University false true UCLA Department of Statistics Seminar Joakim Ekstrom 3:00 PM 2009-10-20T07:32:13-07:00