We com.are correspondence analysis (CA) and the alternative approach using Hellinger distance (HD), for representing categorical data in a contingency table. As both m.thods m.y be appropriate, we introduce a param.te...
详细信息
We com.are correspondence analysis (CA) and the alternative approach using Hellinger distance (HD), for representing categorical data in a contingency table. As both m.thods m.y be appropriate, we introduce a param.ter and define a generalized version of correspondence analysis (GCA) which contains CA and HD as particular cases. Com.arison with alternative approaches are perform.d. We propose a coefficient which globally m.asures the sim.larity between CA and GCA, which can be decom.osed into several com.onents, one com.onent for each principal dim.nsion, indicating the contribution of the dim.nsions on the difference between both representations. Two criteria for choosing the best value of the param.ter are proposed. (c) 2005 Elsevier Inc. All rights reserved.
A random.variable with Pareto distribution is expanded as a series of principal com.onents. A com.arison with the exponential distribution is perform.d, an inequality concerning a function and his derivative is obtain...
详细信息
A random.variable with Pareto distribution is expanded as a series of principal com.onents. A com.arison with the exponential distribution is perform.d, an inequality concerning a function and his derivative is obtained as well as the asym.totic distribution of som. statistics related to Rao's quadratic entropy. (c) 2004 Elsevier B.V. All rights reserved.
暂无评论