Multi-subject longitudinal models with random coefficients and patterned correlation structure

Austrian Science Fund

I propose to study modelling issues in multi-subject longitudinal models with random coefficients and patterned correlation structure. In particular, I plan to study the

• Development of improved specification procedures for multi-subject repeated-measures data.

• Graphical techniques for model specification and model diagnostic checking.

>

• Inference procedures that incorporate orderrestrictions among the fixed effects.

• Estimation of local continuoustime trend components using polynomial smoothing splines.
  
  
• Application of the newly developed procedures to the analysis of several data sets.

The planned research activities are described in this proposal. The relevant literature is reviewed, and initial research findings are presented.


The analysis of repeated measures on panels of subjects is important in many application areas. The class of models which is studied in this proposal, multi-subject longitudinal models, combine both cross-sectional and longitudinal aspects. Many empirical investigations involve the analysis of data structures that are both cross-sectional (that is, observations on several subjects at a specific time period or a specific location) and longitudinal (that is, observations taken over time or space). Multi-subject longitudinal data structures arise in economics and business (where panels of subjects are studied over time), biostatistics (where groups of patients are exposed to different treatments and followed over time), and life-sciences (where the response of animals to different treatments is followed over time).

I am planning on publishing the results of my research in international statistics journals, such as Biometrika, Biometrics, Journal of the American Statistical Association, and Journal of the Royal Statistical Society.