From: The statistical approach in trial-based economic evaluations matters: get your statistics together!
Analysis | Societal costs difference (€) (95% CI) | QALY difference (95% CI) | ICER (€/ QALY gained) |
---|---|---|---|
1.- Two t-tests (1 for cost; 1 for effects) complete-case analysis | −782 (− 4332 to 2768) | −0.001 (− 0.070 to 0.0677) | 636,744 |
2.- Two bootstrapped t-tests; complete-case analysis | −782 (− 4850 to 2544) | − 0.001 (− 0.070 to 0.0677) | 636,744 |
3.- Two regressions with correction for confounders; complete-case analysis | −197 (− 3692 to 3297) | − 0.009 (− 0.077 to 0.058) | 21,390 |
4.- Two bootstrapped regressions with correction for confounders; complete-case analysis | −197 (− 3643 to 2832) | − 0.009 (− 0.077 to 0.058) | 21,390 |
5.- Two t-tests; mean imputation | − 840 (− 3382 to 1701) | 0.004 (− 0.049 to 0.057) | − 231,148 |
6.- Two bootstrapped t-tests; mean imputation | −840 (− 3467 to 1693) | 0.004 (− 0.049 to 0.056) | −231,148 |
7.- Two regressions with correction for confounders; mean imputation | − 707 (− 3197 to 1783) | 0.005 (− 0.047 to 0.057) | − 145,697 |
8.- Two bootstrapped regressions with correction for confounders; mean imputation | −707 (− 3221 to 1636) | 0.005 (− 0.047 to 0.057) | − 231,148 |
9.- Two t-tests; MI | −141 (− 2318 to 2035) | 0.009 (− 0.053 to 0.071) | −16,425 |
10.- Two bootstrapped t-tests; MI | −141 (− 2398 to 1908) | 0.009 (−0.053 to 0.071) | − 16,425 |
11.- Two regressions with correction for confounders; MI | −73 (− 2295 to 1073) | 0.011 (− 0.050 to 0.071) | − 6880 |
12.- Two bootstrapped regressions with correction for confounders; MI | −73 (− 2248 to 1942) | 0.011 (− 0.050 to 0.071) | −6880 |
13.- SUR without correction for confounders; MI | −141 (− 849 to 1164) | 0.009 (− 0.056 to 0.072) | −16,425 |
14.- SUR with correction for confounders; MI | −82 (− 892 to 1586) | 0.011 (− 0.058 to 0.079) | −7502 |