Get access

The Reliability of Measurement and the Cross-Time Stability of Individual and Family Variables

Authors

  • Arland Thornton,

    1. Institute for Social Research, Department of Sociology, Population Studies Center, 4053 ISR, 426 Thompson Street, P.O. Box 1248, The University of Michigan, Ann Arbor, MI 48106-1248 (arlandT@isr.umich.edu).
    Search for more papers by this author
  • Georgina Binstock

    1. Institute for Social Research, Department of Sociology, Population Studies Center, 4053 ISR, 426 Thompson Street, P.O. Box 1248, The University of Michigan, Ann Arbor, MI 48106-1248 (arlandT@isr.umich.edu).
    2. Centro de Estudios de Población, Corrientes 2817 Piso 7, Capital Federal, C1193AAA, Buenos Aires, Argentina.
    Search for more papers by this author

Abstract

Using data from a 31-year panel study, we evaluate both the reliability of measurement of family attitudes, relationships, and self-concepts and the stability of these variables across time. We also compare the reliability of measurement and the stability of variables across time in these domains of family life with the reliability and stability of behavioral dimensions. Our results provide considerable support for the hypothesis that family relationships, attitudes, and self-concepts can be measured reliably. We also demonstrate that self-concepts and family relationships and attitudes have high levels of stability across significant periods of time, and that these are comparable to those for the behavioral indicators we examined.

Get access to the full text of this article

Ancillary