Analysing infant data at the group- or individual-level: The impact of measurement error on sophisticated analyses

The article 'Six solutions for more reliable infant research' by Byers-Heinlein et al. proposes six solutions to improve upon the reliability of infant research. The present commentary supports and expands upon the sixth solution, 'Conduct more sophisticated analyses'. This commentary first focuses on group-level, traditional analytic techniques that infant research has predominantly relied on over the last several decades. Details are provided to expand upon measurement errors in these types of analyses. The second focus is on individual-level, more sophisticated statistical analyses, such as mixed-effects models and structural equation modelling. Details are provided to expand upon how measurement error can impact these types of analyses. Throughout the commentary and in its conclusion, this commentary provides ways in which the other five solutions proposed can contribute to the sixth solution.