Search Results

Author: Parker, Robert N.
Resulting in 1 citation.
1. Campbell, Richard T.
Mutran, Elizabeth
Parker, Robert N.
Longitudinal Design and Longitudinal Analysis: A Comparison of Three Approaches
Research on Aging 8,4 (December 1986): 480-502.
Also: http://roa.sagepub.com/content/8/4/480.abstract
Cohort(s): Older Men
Publisher: Sage Publications
Keyword(s): Age and Ageing; Research Methodology; Retirement

Permission to reprint the abstract has not been received from the publisher.

This paper compares three methods of analyzing data in longitudinal studies of aging: multivariate analysis of variance (MANOVA), the LISREL structural equation method, and event history analysis. The basic concepts of each approach are explained, and each technique is applied to data from the National Longitudinal Surveys of Labor Market Experience to illustrate its use in analyzing factors affecting the retirement decision. The results indicate that each approach has a particular conceptualization of development and change and particular design requirements, and therefore each is appropriate under different data collection regimes. MANOVA is ideal for comparisons of groups over time because its tests are precise and unambiguous, but it does not provide information about the process by which people withdraw from the labor force. The LISREL path analytic approach deals well with the concept of an intervening variable and permits nonadditivity and nonlinearity, but it does not deal well with causal contingencies or permit tests of alternative sequences. Event history or transition models requires exact information on the timing of transitions, and it can be used to estimate a number of models under various assumptions about the form of the underlying transition rate. [AgeLine]
Bibliography Citation
Campbell, Richard T., Elizabeth Mutran and Robert N. Parker. "Longitudinal Design and Longitudinal Analysis: A Comparison of Three Approaches." Research on Aging 8,4 (December 1986): 480-502.