Given the diversity inherent to heritage speaker populations, the theme of this tutorial will be heterogeneity in participants’ language background: how to transparently report it in descriptive statistics and how to account for it in our formal statistical analyses. We will also discuss the pros and cons of continuous versus categorical variables to capture participants’ language background and/or proficiency. The part of the tutorial dedicated to statistical analysis will begin with an intuitive introduction to linear mixed effects models and how to understand random effects, as well as how to interpret statistical output to determine whether a random effect is appropriate and how much variation it captures. Potential contributions of less-commonly used approaches to handling heterogeneity, such as cluster analyses, will also be briefly introduced.