Hi,

I would highly recommend this review to start with longitudinal data analysis:

Title: An overview of longitudinal data analysis methods for neurological research

Link: http://www.ncbi.nlm.nih.gov/pubmed/22203825

They talk about both pros and cons of:

Traditional methods (not recommended):

1. Simple regression of the dependent variable on the time measure
2. Analyzing a single summary number that indexes change for each subject
3. A GLM approach with a fixed-subject effect

Current methods (recommended under restrictive situations):

1. Repeated-measure ANCOVA
2. ANCOVA for two time points
3. GEE (Generalized Estimating Equation)
4. Latent curve growth models

In more general cases, they advise using:

1. Random-effect models

From there you can look into each method in more detail and then use which suits your requirement. I hope this helps.

Another one is from Bodo Winter: Linear models and linear mixed effects models in R with linguistic applications. arXiv:1308.5499. http://arxiv.org/pdf/1308.5499.pdf