Chaturvedi, Anil; Green, Paul E.; Caroll, J. Douglas - In: Journal of Classification 18 (2001) 1, pp. 35-55
We norm (defined as the limit of an L<Subscript>p</Subscript> norm as p approaches zero). In Monte Carlo simulations, both K-modes and the latent class procedures (e.g., Goodman 1974) performed with equal efficiency in recovering a known underlying cluster structure. However, K-modes is an order of magnitude faster...</subscript>