Running Head: SUBCLASSIFICATION OF SPEECH SOUND DISORDERS 1 Data-Driven Subclassification of Speech Sound Disorders in Preschool Children

Purpose: The purpose of the study was to determine whether distinct subgroups of preschool children with speech sound disorders (SSD) could be identified using a subgroup discovery algorithm (SUBARP). Of specific interest was finding evidence of a subgroup of SSD exhibiting performance consistent with atypical speech motor control. Method: Ninety-seven preschool children with SSD completed speech and nonspeech tasks. Fifty-three kinematic, acoustic, and behavioral measures from these tasks were input to SUBARP. Results: Two distinct subgroups were identified from the larger sample. The first subgroup (76%; population prevalence estimate: 67.8-84.8%) did not have characteristics that would suggest atypical speech motor control. The second subgroup (10.3%; population prevalence estimate: 4.3-16.5%) exhibited significantly higher variability in measures of articulatory kinematics and poor ability to imitate iambic lexical stress, suggesting atypical speech motor control. Both subgroups were consistent with classes of SSD in the Speech Disorders Classification System (SDCS; Shriberg et al., 2010a). Characteristics of children in the larger subgroup are consistent with the proportionally large SDCS class termed Speech Delay; characteristics of children in the smaller subgroup are consistent with the SDCS subtype termed Motor Speech Disorder-Not Otherwise Specified. Candidate measures to identify children in each of these groups were identified.