Determine the Composite Reliability of a Naturalistic, Unbalanced Dataset R package CompositeReliability version 1.0.3 The reliability of assessment tools is a crucial aspect of monitoring student performance in various educational settings. It ensures that the assessment outcomes accurately reflect a student's true level of performance. However, when assessments are combined, determining composite reliability can be challenging, especially for naturalistic and unbalanced datasets. This package provides an easy-to-use solution for calculating composite reliability for different assessment types. It allows for the inclusion of weight per assessment type and produces extensive G- and D-study results with graphical interpretations. Overall, our approach enhances the reliability of composite assessments, making it suitable for various education contexts. Software Depends: R (>= 2.10) Imports: dplyr, ggplot2, lme4, magrittr, plyr, psych, reshape2, tidyr, Rsolnp Joyce Moonen - van Loon <j.moonen@maastrichtuniversity.nl> Comprehensive R Archive Network (CRAN) Joyce Moonen - van Loon [aut, cre] (ORCID: <https://orcid.org/0000-0002-8883-8822>) GPL (>= 3) 2023-08-21 application/tgz https://CRAN.R-project.org/package=CompositeReliability doi:10.32614/CRAN.package.CompositeReliability