From Euclidean distances to APC models

作     者：De Santis, Gustavo Mucciardi, Massimo 

作者机构：Univ Florence DiSIA Dept Stat Informat Applicat G Parenti Florence Italy Univ Messina Dept Econ Messina Italy 

出 版 物：《QUALITY & QUANTITY》 (质与量)

年 卷 期：2017年第51卷第2期

页      面：829-846页

核心收录：

学科分类：0303[法学-社会学] 03[法学] 0714[理学-统计学（可授理学、经济学学位）] 

主　　题：APC (age period cohort) models Clusters Cultural distance EM algorithm Euclidean distance Quantile regression 

摘      要：In this paper we show that a recently developed method for the study of cultural differences, called DBS-EM, or Distance Between Strata estimated with the EM (Expectation Maximization) algorithm, can also be used to circumvent the difficulties posed by APC (or Age, Period, Cohort) models. The DBS-EM method produces an original measure of the distance (dependent variable) between any two subsets of observations (strata) within a sample, where the stratification variables can be interpreted as regressors. When these stratification variables are age, period, and cohort, what results is an APC model which, however, proves immune to the intrinsic collinearity problem (C = P-A). With a few limitations, to be sure, which are discussed in the article. In our application to Italian data over the years 1993-2013, age and cohort strongly shape cultural consumption, while cohort and period impact, but only up to a point, on political participation.