Using linear mixed models to analyze data from eye-tracking research on subtitling

Abstract In this paper, we aim to promote the use of linear mixed models (LMMs) in eye-tracking research on subtitling. Using eye tracking study viewers’ reading subtitles often warrants controlling for many confounding variables. However, even assuming that these variables are known researchers, such control may not be possible or desired. Traditional statistical methods as t -tests ANOVAs exacerbate problem due aggregated data: each participant has one data point per dependent variable. As a solution, propose LMMs, which better suited account number subtitle and characteristics, thus explaining more variance. We introduce essential theoretical aspects LMMs highlight some their advantages over traditional methods. To illustrate our point, compare two analyses same dataset: using -test; another LMMs.