Multidimensional Signals and Analytic Flexibility: Estimating Degrees of Freedom in Human-Speech Analyses
Stefano Coretta, Joseph V. Casillas, Simon Roessig, Michael Franke, Byron Ahn, Ali H. Al‐Hoorie, Jalal Al‐Tamimi, Najd E. Alotaibi, Mohammed K. AlShakhori, Ruth Altmiller, Pablo R. Arantes, Angeliki Athanasopoulou, Melissa M. Baese‐Berk, George Bailey, Cheman Baira A Sangma, Eleonora J. Beier, Gabriela M. Benavides, Nicole Benker, Emelia P. BensonMeyer, Nina R. Benway, Grant M. Berry, Liwen Bing, Christina Bjorndahl, Mariška Bolyanatz, Aaron Braver, Violet A. Brown, Alicia M. Brown, Alejna Brugos, Erin Michelle Buchanan, Tanna Butlin, Andrés Buxó‐Lugo, Coline Caillol, Francesco Cangemi, Christopher Carignan, Sita Carraturo, Tiphaine Caudrelier, Eleanor Chodroff, Michelle Cohn, Johanna Cronenberg, Olivier Crouzet, Erica L. Dagar, Charlotte Dawson, Carissa A. Diantoro, Marie Dokovova, Shiloh Drake, Fengting Du, Margaux Dubuis, Florent Duême, Matthew Durward, Ander Egurtzegi, Mahmoud Medhat Elsherif, Janina Esser, Emmanuel Ferragne, Fernanda Ferreira, Lauren Fink, Sara Finley, Kurtis Foster, Paul Foulkes, Rosa Franzke, Gabriel Frazer-McKee, Robert Fromont, Christina García, Jason Geller, Camille L. Grasso, Pia Greca, Martine Grice, Magdalena Grose‐Hodge, Amelia Gully, Caitlin Halfacre, Ivy Hauser, Jen Hay, Robert Haywood, Sam Hellmuth, Allison Hilger, Nicole Holliday, Damar Hoogland, Yaqian Huang, Vincent Hughes, Ane Icardo Isasa, Zlatomira G. Ilchovska, Hae‐Sung Jeon, Jacq Jones, Mágat N. Junges, Stephanie Kaefer, Constantijn Kaland, Matthew C. Kelley, Niamh Kelly, Thomas Kettig, Ghada Khattab, Ruud Koolen, Emiel Krahmer, Dorota Krajewska, Andreas Krug, Abhilasha Ashok Kumar, Anna Lander, Tomas O. Lentz, Wanyin Li, Yanyu Li, Maria Lialiou, Ronaldo Mangueira Lima
Abstract
Recent empirical studies have highlighted the large degree of analytic flexibility in data analysis that can lead to substantially different conclusions based on the same data set. Thus, researchers have expressed their concerns that these researcher degrees of freedom might facilitate bias and can lead to claims that do not stand the test of time. Even greater flexibility is to be expected in fields in which the primary data lend themselves to a variety of possible operationalizations. The multidimensional, temporally extended nature of speech constitutes an ideal testing ground for assessing the variability in analytic approaches, which derives not only from aspects of statistical modeling but also from decisions regarding the quantification of the measured behavior. In this study, we gave the same speech-production data set to 46 teams of researchers and asked them to answer the same research question, resulting in substantial variability in reported effect sizes and their interpretation. Using Bayesian meta-analytic tools, we further found little to no evidence that the observed variability can be explained by analysts’ prior beliefs, expertise, or the perceived quality of their analyses. In light of this idiosyncratic variability, we recommend that researchers more transparently share details of their analysis, strengthen the link between theoretical construct and quantitative system, and calibrate their (un)certainty in their conclusions.