Issues in Aggregating Time Series: Illustration Through an AR(1) Model
Intra-individual variation is time dependent variation within a single participant’s time series. When data are collected from more than one subject, methods developed for single subject intra-individual relationship may not fully work and laws governing inter-individual relationship may not apply to intra-individual relationship. There are relative few methods in dealing with the analysis of pooling multiple time series. This article aims to investigate empirically the comparability of methods for pooling time series data and to address related issues through an AR(1) model. In this article, multiple time series are formulated, pooling estimation methods are derived and compared, simulation studies results are summarized, and related practical issues are addressed.
KeywordsTime series analysis First-order autoregressive model Pooling multiple subjects Longitudinal analysis Maximum likelihood estimation
- Cattell, R. B., & Scheier, I. H. (1961). The meaning and measurement of neuroticism and anxiety. New York: Ronald.Google Scholar
- Molenaar, P. C. M. (2004). A manifesto on psychology as idiographic science: Bringing the person back into scientific psychology—this time forever. Measurement: Interdisciplinary Research and Perspectives, 2, 201–218.Google Scholar
- Molenaar, P. C. M., Huizenga, H. M., & Nesselroade, J. R. (2003). The relationship between the structure of interindividual and intraindividual variability: A theoretical and empirical vindication of developmental systems theory. In U. M. Staudinger & U. Lindenberger (Eds.), Understanding human development: Dialogues with lifespan psychology (pp. 339–360). Norwell: Kluwer Academic Publishers.Google Scholar
- Nesselroade, J. R., & Molenaar, P. (2003). Quantitative models for developmental processes. In J. Valsiner & K. Connolly (Eds.), Handbook of developmental psychology (pp. 622–639). London: Sage.Google Scholar
- Nesselroade, J. R., & Molenaar, P. C. M. (1999). Pooling lagged covariance structures based on short, multivariate time-series for dynamic factor analysis. In R. H. Hoyle (Ed.), Statistical strategies for small sample research (pp. 224–250). Newbury Park, CA: Sage.Google Scholar