Whittaker Awarded AERA Grant to Study the Impact of Interindividual Variability in Latent Growth Models

headshot

Dr. Tiffany Whittaker was awarded $20,000 to support her methodological research on latent growth models. With K-12 education reform at the forefront of discussion among national-, state-, and district-level leaders, especially with respect to college- and career-ready standards, the assessment of educational progress across time has been highly recommended. Standard regression techniques have been used in order to establish benchmarks for college and career readiness which are limited with respect to the use of composite measures and assessing growth across time. Latent growth modeling (LGM) within the structural equation modeling arena is a popular and flexible tool with which researchers may examine longitudinal change/growth of various outcomes.

When modeling longitudinal growth, various time-coding and centering techniques may be used that render meaningful conclusions. However, parameter estimates of interest in a latent growth model become more inaccurate under increased levels of interindividual heterogeneity (e.g., varying ages and/or varying measurement occasions within a measurement occasion/wave).

The purpose of this study will be to:

  1. examine the types of interindividual heterogeneity and the corresponding amount of interindividual heterogeneity within two large-scale datasets; and
  2. examine the impact of different time-coding and centering strategies to the large-scale datasets as well as to data simulated under varied conditions.

The National Educational Longitudinal Study of 1988 (NELS 88) and the National Longitudinal Survey of Youth 1997 (NLSY97) data sets will be used. It is hoped that this research will provide meaningful information about which time-coding and centering strategies are more optimal when interindividual heterogeneity exists in longitudinal data, resulting in more accurate assessments of educational progress across time.

Last updated on January 9, 2013