Samples in Applied Psychology: Over a Decade of Research in Review

• 成果类型: Article
• 署名作者: Shen, Winny; Kiger, Thomas B.; Davies, Stacy E.; Rasch, Rena L.; Simon, Kara M.; Ones, Deniz S.
• 署名单位: University of Minnesota System; University of Minnesota Twin Cities
• 刊物名称: JOURNAL OF APPLIED PSYCHOLOGY
• ISSN/ISSBN: 0021-9010
• DOI: 10.1037/a0023322
• 发表日期: 2011
• 页码: 1055-1064
• 关键词: sample size; statistical power; methodology; Experimental design

摘要

This study examines sample characteristics of articles published in Journal of Applied Psychology (JAP) from 1995 to 2008. At the individual level, the overall median sample size over the period examined was approximately 173, which is generally adequate for detecting the average magnitude of effects of primary interest to researchers who publish in JAP. Samples using higher units of analyses (e. g., teams, departments/work units, and organizations) had lower median sample sizes (Mdn approximate to 65), yet were arguably robust given typical multilevel design choices of JAP authors despite the practical constraints of collecting data at higher units of analysis. A substantial proportion of studies used student samples (similar to 40%); surprisingly, median sample sizes for student samples were smaller than working adult samples. Samples were more commonly occupationally homogeneous (similar to 70%) than occupationally heterogeneous. U. S. and English-speaking participants made up the vast majority of samples, whereas Middle Eastern, African, and Latin American samples were largely unrepresented. On the basis of study results, recommendations are provided for authors, editors, and readers, which converge on 3 themes: (a) appropriateness and match between sample characteristics and research questions, (b) careful consideration of statistical power, and (c) the increased popularity of quantitative synthesis. Implications are discussed in terms of theory building, generalizability of research findings, and statistical power to detect effects.