Functional Mixed effects Model for Joint Analysis of Longitudinal and Cross-Sectional Growth Data
By: Long Chen, Ji Chen, Yingchun Zhou
Potential Business Impact:
Finds growth patterns in mixed-up data.
A new method is proposed to perform joint analysis of longitudinal and cross-sectional growth data. Clustering is first performed to group similar subjects in cross-sectional data to form a pseudo longitudinal data set, then the pseudo longitudinal data and real longitudinal data are combined and analyzed by using a functional mixed effects model. To account for the variational difference between pseudo and real longitudinal growth data, it is assumed that the covariance functions of the random effects and the variance functions of the measurement errors for pseudo and real longitudinal data can be different. Various simulation studies and real data analysis demonstrate the good performance of the method.
Similar Papers
Variable Selection for Fixed and Random Effects in Multilevel Functional Mixed Effects Models
Methodology
Finds how age/race change daily activity patterns.
Semiparametric Growth-Curve Modeling in Hierarchical, Longitudinal Studies
Methodology
Tracks how things grow or shrink more accurately.
Multivariate longitudinal modeling of cross-sectional and lagged associations between a continuous time-varying endogenous covariate and a non-Gaussian outcome
Methodology
Helps doctors understand disease changes better.