Skip to main content

Table 2 Bootstrapped Power Calculationsa

From: Prospective multicenter randomized patient recruitment and sample collection to enable future measurements of sputum biomarkers of inflammation in an observational study of cystic fibrosis

Row Statistical Model Outcome Variable Biomarker, Concentration or Activity Percent Power α-Level Estimate of Patients Required
1 Proportional Hazards Time to first Pulmonary Exacerbation HMGB-1 90 0.01 40
2 Proportional Hazards Time to Lung Transplantation or Death HMGB-1 90 0.01 30
3 Linear Regression Acute FEV1% Drop with onset of a Pulmonary Exacerbation GMCSF 80 0.01 175
4 Linear Regression Acute FEV1% Drop with onset of a Pulmonary Exacerbation GMCSF 85 0.05 125
5 Linear Regression FEV1% Drop over 2 Years NE 80 0.05 32
  1. aBased on prior published results, we sampled patients and bootstrapped statistical models of predictor biomarkers for outcome variables, setting percent power and α-level in order to estimate the number of patients similar to prior patients needed to detect associations. See the study protocol for more details (Additional file 5)