About us |
People |
Research |
Courses |
Effect Magnification
Artificial effect size magnification (ESM) may occur in underpowered studies, where effects are only reported because they or their associated p-value have passed some threshold. The plausibility of findings for a specific study can be evaluated by computation of ESM, which requires statistical simulation. Evaluating ESM allows assessing the reliability of reported effect sizes and to put an observed statistically significant effect size into a fuller context with respect to potential implications for study conclusions. |
|
Papers
Miller, D. J., Nguyen, J. T., and Bottai, M. emagnification: a tool for estimating effect size magnification and performing design calculations in epidemiological studies. The Stata Journal, Volume 20 Number 3: pp. 548-564 Miller, D. J., Nguyen, J. T., and Bottai, M. emagnification: a tool for estimating effect size magnification and performing design calculations in epidemiological studies. Working Paper 2019 Software Download the emagnification command in Stata: net install emagnification, from(http://www.imm.ki.se/biostatistics/stata) replace Download the emagnification SAS macro: ESM proportion.sas ESM rate.sas |
Presentations
August 24-27, 2020 Effect Size Magnification and Epidemiologic Design Calculations. Use in EPA's Office of Pesticide Programs in evaluating study size in epidemiology studies 32nd Annual Conference of the International Society for Environmental Epidemiology (virtual conference) August 30, 2019 emagnification: A tool for estimating effect-size magnification and performing design calculations in epidemiological studies 2019 Nordic and Baltic Stata Users Group Meeting, Stockholm, Sweden |
Unit of Biostatistics, Nobels väg 13, Karolinska Institutet, 17177 Stockholm, Sweden |