Using machine learning to understand age and gender classification based on infant temperament

• Authors: Maria A Gartstein, Washington State University Pullman; Erich D Seamon, University of Idaho; Jennifer A Mattera, Washington State University Pullman; Michelle Bosquet Enlow, Harvard Medical School; Rosalind J Wright, Kravis Children's Hospital; Koraly Perez-Edgar, Pennsylvania State University; Kristin A Buss, Pennsylvania State University; Vanessa LoBue, Rutgers University–New Brunswick; Martha A Bell, Virginia Polytechnic Institute and State University; Sherryl Goodman, Emory University; Susan Spieker, University of Washington; David J Bridgett, Northern Illinois University; Amy L Salisbury, Virginia Commonwealth University; Megan R Gunnar, University of Minnesota Twin Cities; Shanna B Mliner, University of Minnesota Twin Cities; Maria Muzik, University of Michigan, Ann Arbor; Cynthia A Stifter, Pennsylvania State University; Elizabeth M Planalp, University of Wisconsin-Madison; Samuel A Mehr, Harvard University; Elizabeth S Spelke, Harvard University; Angela F Lukowski, University of California, Irvine; Ashley M Groh, University of Missouri; Diane M Lickenbrock, Western Kentucky University; Rebecca Santelli, The University of North Carolina at Chapel Hill; Tina Du Rocher Schudlich, Western Washington University; Stephanie Anzman-Frasca, University at Buffalo, The State University of New York; Catherine Thrasher, University of Virginia; Anjolii Diaz, Ball State University; Carolyn Dayton, Wayne State University; Kameron J Moding, Purdue University; Evan M Jordan, Oklahoma State University
• Journal Title: PLoS ONE
• Volume: Volume 17, Number 4 April
• Publisher: PLOS | 2022-04-01, Pages e0266026-e0266026
• Type of Work: Article | Final Publisher PDF
• Publisher DOI: http://doi.org/10.1371/journal.pone.0266026
• Subjects: Health Sciences, Medicine and Surgery
• Keywords: Child; Child, Preschool; Fear; Female; Humans; Infant; Infant Behavior; Machine Learning; Male; Surveys and Questionnaires; Temperament

Abstract

Age and gender differences are prominent in the temperament literature, with the former particularly salient in infancy and the latter noted as early as the first year of life. This study represents a meta-analysis utilizing Infant Behavior Questionnaire-Revised (IBQ-R) data collected across multiple laboratories (N = 4438) to overcome limitations of smaller samples in elucidating links among temperament, age, and gender in early childhood. Algorithmic modeling techniques were leveraged to discern the extent to which the 14 IBQ-R subscale scores accurately classified participating children as boys (n = 2,298) and girls (n = 2,093), and into three age groups: youngest (< 24 weeks; n = 1,102), mid-range (24 to 48 weeks; n = 2,557), and oldest (> 48 weeks; n = 779). Additionally, simultaneous classification into age and gender categories was performed, providing an opportunity to consider the extent to which gender differences in temperament are informed by infant age. Results indicated that overall age group classification was more accurate than child gender models, suggesting that age-related changes are more salient than gender differences in early childhood with respect to temperament attributes. However, gender-based classification was superior in the oldest age group, suggesting temperament differences between boys and girls are accentuated with development. Fear emerged as the subscale contributing to accurate classifications most notably overall. This study leads infancy research and meta-analytic investigations more broadly in a new direction as a methodological demonstration, and also provides most optimal comparative data for the IBQ-R based on the largest and most representative dataset to date.