Using Linear Mixed-Effects Models to Analyze Historical Trends in Performance Strategies Commentary on Majid Motavasseli's Article "Interpretation of Cyclic Form in Bach's 'Goldberg Variations' through

The usefulness of advanced statistical approaches in performance-based analysis has been demonstrated in several recent publications. Here, I expand on Majid Motavasseli's article "Interpretation of Cyclic Form in J. S. Bach's "Goldberg Variations" through Performance History" (2021) by applying his data to further address issues related to the performance history of the "Goldberg Variations." Using a tempo measurement database comprising seventy-six selected recordings of the "Goldberg" cycle, I built a linear mixed-effects model predicting the main tempo for each recording from the following parameters: performer, variation number, instrument (piano or harpsichord), year of recording, variation type, and finally mode (major/minor) of the variation. Two statistically significant interactions emerged: a two-way interaction between instrument and mode, and a three-way interaction between instrument, year of recording, and variation type. I discuss the musical meaning of these interactions and suggest further avenues for applying advanced statistical approaches in the field of music performance research.