Sample size estimation for the diagnostic impact outcome one antibiotic arm to standard of care arm (pairwise comparison)
| Power (X2 difference between independent proportions) | Effect size (50% SoC vs 60% amoxycillin or azithromycin) | Effective sample per arm (sputum negative participants needed) |
| 0.80 | 0.10 | 388 |
| 0.85 | 0.10 | 443 |
| 0.90 | 0.10 | 519 |
Highlighted entries indicates target power and respective sample size estimates based on knowledge of TB risk, ability to produce and submit sputum, and loss to follow-up.
Stata code: power two proportions 0.5 and 0.6, test (χ2), power (0.80), n ratio (1).
SoC, standard of care; TB, tuberculosis.