A generalized linear mixed effect model (GLMM) with a Gamma distribution and a log link function was used to compare the growth of juvenile corals (surface area over nine weeks) among different light spectra treatments. A general linear mixed effect model was chosen to account for the effects of random factors, including the random intercept and slope of tile and individual coral, which may cause variation over time. The most complex model was built, including all fixed predictors (light spectrum, species, and time) and their interactions. A backward stepwise method was used to remove non-significant and multicollinear variables and interactions from the model.

To investigate the effect of light spectra and species (fixed factors) on survival over time, a survival analysis, specifically a Cox proportional hazard model, was used. The Kaplan-Meier estimator was utilized to generate survival curves and visualize mortality among treatment groups.