首页    期刊浏览 2024年12月19日 星期四
登录注册

文章基本信息

  • 标题:Configural Frequency Analysis (CFA), Multiple Correspondence Analysis (MCA) and Latent Class Analysis (LCA): An empirical comparison
  • 本地全文:下载
  • 作者:Erwin Lautsch ; Michael M. Plichta
  • 期刊名称:Psychology Science
  • 印刷版ISSN:1614-9947
  • 出版年度:2003
  • 卷号:45
  • 期号:02
  • 出版社:Pabst Science Publishers
  • 摘要:

    CFA, MCA and LCA are well known methods in categorical data analyses. In the present study CFA is applied as an instrument in terms of type exploration and confirmation. MCA and LCA are used by means of a more detailed description and explanation of statistically significant types. To demonstrate the combined use of the mentioned techniques the data-set of the 14th Shell Youth Study 2002 is used (herein focusing on attitudes of young adults towards social organizations and political institutions). CFA identifies three types; MCA and LCA enable us to (complementary) represent and interpret the relational structure of the identified types on manifest as well as latent measurement levels. On the manifest level types can be understood as categories of an ordinal confidence-scale. Latent level perspective provides evidence for a specific locus of all three found types in latent space. All analyses (CFA, MCA and LCA) are performed with software LEM (Vermunt, 1997).

  • 关键词:Configural Frequency Analysis (CFA), Multiple Correspondence Analysis (MCA), Latent Class Analysis (LCA), exploration and confirmation of types, ontogenesis of types, manifest and latent variable, comparative interpretation of the methods, software: LEM
国家哲学社会科学文献中心版权所有