Analytical strategies in human growth research.
Bottom Line: A summary table linking each analytical strategy to its applications is provided to help investigators match their hypotheses and measurement schedules to an analysis plan.All too often, serial measurements are treated as cross-sectional in analyses that do not harness the power of longitudinal data.The broad goal of this article is to encourage the rigorous application of longitudinal statistical methods to human growth research.
Affiliation: MRC Unit for Lifelong Health and Ageing at UCL, London, WC1B 5JU, United Kingdom.Show MeSH
Related in: MedlinePlus
Mentions: Readers wanting to explore the algebra of latent growth curve models are directed to the book “Latent Curve Models: A Structural Equation Perspective” (Bollen and Curran, 2006). For the purpose of the present article, Figure 1 provides a pictorial representation of a latent curve growth model. In this example, there are three latent variables in circles that together describe a quadratic polynomial curve. The repeated measures of weight in rectangular boxes are related to the latent variables through factor loadings, which are generally specified a priori. All of the loadings for the intercept factor are set to one, so that it equally influences all of the serial measurements; the loadings for the linear factor reflect the passage of age, and are equally spaced because of the uniform age between consecutive assessments; and the loadings for the second factor reflect the passage of age squared (Bollen and Curran, 2006). The child specific F-scores for the intercept and linear factors are equivalent to the respective random effects estimates in the model in the previous section. The variance of the quadratic factor in the latent growth curve model could even be constrained to be zero, thereby making the two models identical.
Affiliation: MRC Unit for Lifelong Health and Ageing at UCL, London, WC1B 5JU, United Kingdom.