Detecting and correcting attrition bias in longitudinal family research.
Given that bias resulting from the attrition of respondents poses a threat to the internal and external validity of findings in longitudinal family research, the writers present methods for detecting and correcting attrition bias in such research. He discusses how external validity is threatened by...
| Publicado en: | Journal of Marriage & Family Vol. 57; pp. 921 - 930 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
Wiley-Blackwell
November 1995
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| Sumario: | Given that bias resulting from the attrition of respondents poses a threat to the internal and external validity of findings in longitudinal family research, the writers present methods for detecting and correcting attrition bias in such research. He discusses how external validity is threatened by the differences in characteristics between two samples at initial and subsequent waves and how internal validity is affected by differences in the relationships between variables in the samples. Having considered different methods of detecting attrition bias, he presents J.J. Heckman's procedure for correcting attrition bias. He then uses data from the University of Southern California Longitudinal Study of Generations to analyze change in grandparents' face-to-face contact with a designated grandchild over a 14-year period in order to demonstrate both the detection and correction of attrition bias. |
|---|