TY - JOUR
AU1 - Fink, Aliza K.
AB - ORIGINAL ARTICLE Semi-Automated Sensitivity Analysis to Assess Systematic Errors in Observational Data Timothy L. Lash and Aliza K. Fink precision, and those deriving from systematic error, which is Background: Published epidemiologic research usually provides a 2-5 assessed by the effect measure’s validity. If the error about quantitative assessment of random error for effect estimates, but no an effect estimate equals its difference from the truth, then the quantitative assessment of systematic error. Sensitivity analysis can random error is that which approaches zero as the study size provide such an assessment. Methods: We describe a method to reconstruct epidemiologic data, increases, and the systematic error is that which does not. A accounting for biases, and to display the results of repeated recon- quantitative assessment of the systematic error for an effect structions as an assessment of error. We illustrate with a study of the estimate can be made by sensitivity analysis. effect of less-than-definitive therapy on breast cancer mortality. To improve the precision of an effect estimate, epide- Results: We developed SAS code to reconstruct the data that would miologists design their studies to gather as much information have been observed had a set of systematic errors been absent, and 
TI - Semi-Automated Sensitivity Analysis to Assess Systematic Errors in Observational Data
JF - Epidemiology
DO - 10.1097/01.EDE.0000071419.41011.cf
DA - 2003-07-01
UR - https://www.deepdyve.com/lp/wolters-kluwer-health/semi-automated-sensitivity-analysis-to-assess-systematic-errors-in-156G8rmKD0
SP - 451
EP - 458
VL - 14
IS - 4
DP - DeepDyve
ER -