Controlling for false negatives in agent-based models: a review of power analysis in organizational research

摘要: This article is concerned with the study of statistical power in agent-based modeling (ABM). After an overview classic statistics theory on how to interpret Type-II error (whose occurrence also referred as a false negative) and power, manuscript presents ABM simulation articles published management journals other outlets likely publish organizational research. Findings show that most studies are underpowered, some being overpowered. discussing risks under- overpower, we present two formulas approximate number runs reach appropriate level power. The concludes importance for behavior scholars perform their models attempt 0.95 or higher at 0.01 significance level.