Quality of statistical reporting in developmental disability journals Aravind K. Namasivayam a,b , Tina Yan a , Wing Yiu Stephanie Wong a and Pascal van Lieshout a,b,c,d,e Null hypothesis significance testing (NHST) dominates quantitative data analysis, but its use is controversial and has been heavily criticized. The American Psychological Association has advocated the reporting of effect sizes (ES), confidence intervals (CIs), and statistical power analysis to complement NHST results to provide a more comprehensive understanding of research findings. The aim of this paper is to carry out a sample survey of statistical reporting practices in two journals with the highest h5-index scores in the areas of developmental disability and rehabilitation. Using a checklist that includes critical recommendations by American Psychological Association, we examined 100 randomly selected articles out of 456 articles reporting inferential statistics in the year 2013 in the Journal of Autism and Developmental Disorders (JADD) and Research in Developmental Disabilities (RDD). The results showed that for both journals, ES were reported only half the time (JADD 59.3%; RDD 55.87%). These findings are similar to psychology journals, but are in stark contrast to ES reporting in educational journals (73%). Furthermore, a priori power and sample size determination (JADD 10%; RDD 6%), along with reporting and interpreting precision measures (CI: JADD 13.33%; RDD 16.67%), were the least reported metrics in these journals, but not dissimilar to journals in other disciplines. To advance the science in developmental disability and rehabilitation and to bridge the research-to-practice divide, reforms in statistical reporting, such as providing supplemental measures to NHST, are clearly needed. International Journal of Rehabilitation Research 38:364–369 Copyright © 2015 Wolters Kluwer Health, Inc. All rights reserved. International Journal of Rehabilitation Research 2015, 38:364–369 Keywords: developmental disability, effect size, null hypothesis significance testing, statistical reporting a Oral Dynamics Laboratory, Department of Speech-Language Pathology, b Toronto Rehabilitation Institute (TRI), c Institute for Biomaterials and Biomedical Engineering (IBBME), d Rehabilitation Sciences Institute, University of Toronto, Toronto and e Human Communications Laboratory (HCL), Department of Psychology, University of Toronto Mississauga, Mississauga, Ontario, Canada Correspondence to Aravind K. Namasivayam, PhD, Oral Dynamics Laboratory, Department of Speech-Language Pathology, University of Toronto, 160-500 University Avenue, Toronto, ON, Canada M5G 1V7 Tel: + 1 416 946 8552; fax: + 1 416 978 1596; e-mail: a.namasivayam@utoronto.ca Received 7 April 2015 Accepted 19 September 2015 Introduction Researchers and clinicians in the area of developmental disability and rehabilitation seek a variety of sources for acquiring and disseminating information. These may be newsletters, blogs, websites, and most importantly, peer- reviewed journals (Chan et al., 2014). Null hypothesis significance testing (NHST) dominates quantitative data analysis in behavioral, social, and life-science journals (Fidler et al., 2005; Kalinowski and Fidler, 2010). For example, NHST was reported in more than 95% of the articles published in leading psychology journals (from 1998 to 2006; Cumming et al., 2007). However, NHST is often misconceived and is the topic of numerous con- troversies [Kalinowski and Fidler, 2010; for more details on this, see Vicente and Torenvliet (2000)]. In essence, statistical significance testing and inferential statistics aim to assess whether or not a ‘positive’ finding can be because of chance in the case where the null hypothesis is valid, but do not address the magnitude of change or the importance of the results in terms of practical or clinical significance (Vacha-Haase and Thompson, 2004). Several disciplines, such as psychology, medicine, and education, have launched major campaigns to reform statistical practices related to NHST: to either altogether avoid NHST approaches or to report NHST with sup- plementary information such as effect sizes (ES) (Thompson, 1996; Vicente and Torenvliet, 2000; Henson, 2006; Fidler and Cumming, 2007). Notably, the American Psychological Association (APA) has advocated the reporting of ES, confidence intervals (CIs), and extensive data descriptions, in addition to reporting NHST results, to provide a more comprehen- sive understanding of research findings (American Psychological Association, 2010, p.33). The first call (in the field of psychology) for such changes in reporting requirements by APA was in 2001, following the Wilkinson and APA Task Force on Statistical Inference in 1999. Although it has been almost 15 years since the call for changes in reporting requirements was made, several journal reviews, including those in other fields, indicate that reporting practices remain inconsistent (Sun et al., 2010; Fritz et al., 2012). For example, in the top four peer-reviewed periodicals published by the American Speech-Language-Hearing Association, ES statistics were reported in 27.7% (range of 13–72%) of articles 364 Original article 0342-5282 Copyright © 2015 Wolters Kluwer Health, Inc. All rights reserved. DOI: 10.1097/MRR.0000000000000138 Copyright r 2015 Wolters Kluwer Health, Inc. All rights reserved.