Linear mixed-effects modeling is necessary when analyzing grouped data that are particularly common in forestry. Sampling designs in forestry are often hierarchical in nature such as in large-scale field blocked experiments and multistage forest inventory. Other grouped data that are often encountered in forestry are longitudinal data and repeated measures such as forest growth and yield data. It is important for modeling and analysis to properly account for correlation presented in grouped data so that interpretation of results is valid. This course will introduces theory of linear mixed-effects modeling and focuses on its application particularly using examples of hierarchical datasets with autocorrelation. An emphasis will be placed on the process of model-building including examining spatial and temporal autocorrelation and weighting. The course will be taught in English.