Mixed noninferiority margin and statistical tests in active controlled trials.
ABSTRACT In an active controlled noninferiority trial without a placebo arm, one of the major considerations is the selection of the noninferiority margin. Although the ICH E10 guideline provides general principles for the selection of appropriate noninferiority margins, there are no established rules or gold standards for the selection of noninferiority margins in active control trials. Hung et al. (2003) proposed a margin selection based on relative risk. However, with relative risk, it is difficult to adjust for covariates. On the other hand, Chow and Shao (2006) proposed a method for selecting noninferiority margins based on treatment difference. The determination of noninferiority margin based on either a test for treatment difference or a test for relative risk would be critical. In this paper, we propose a method for noninferiority testing with the use of a mixed null hypothesis. The mixed null hypothesis consists of a margin based on treatment difference and a margin based on relative risk. Both noninferiority margins will simultaneously satisfy the principles as described in the ICH E10 guideline. Statistical tests for mixed noninferiority margin are also derived. An example concerning the efficacy of a test therapy to an active control on a clinical adverse event in the target patient population with cardiovascular disease is presented to illustrate the proposed method. Simulation studies were also conducted to assess the type I error rate and the power.
Article: Comparison of once- versus twice-daily administration of insulin detemir, used with mealtime insulin aspart, in basal-bolus therapy for type 1 diabetes: assessment of detemir administration in a progressive treat-to-target trial (ADAPT).[show abstract] [hide abstract]
ABSTRACT: The purpose of this study was to compare effects of insulin detemir once daily versus twice a day in a basal-bolus insulin regimen. In this open-label, 7-month study, 520 patients with type 1 diabetes were randomly assigned to receive detemir once daily or twice daily with mealtime insulin aspart. Insulin doses were titrated over 1 month, with patients followed up over the subsequent 3 months. Thereafter, patients were able to switch from one regimen to the other, with an additional nonrandomized 3-month follow-up, to a total of 7 months. The primary end point was A1C at 4 months, with noninferiority defined as a difference <0.4% between groups. A1C at 4 months was 8.1 +/- 0.9 versus 8.0 +/- 1.0% with once- and twice-daily detemir, respectively, with an adjusted between-group difference of 0.12% (95% CI -0.01 to 0.25%), showing noninferiority for once-daily dosing. Similar results were found in the per protocol population. Improvement in A1C was similar in both groups (-0.4 +/- 0.8 vs. -0.5 +/- 0.8%; P = 0.09, NS) but with differences in the 7-point glucose profile. Detemir doses were lower (29 +/- 18 vs. 39 +/- 20 units/day, P < 0.001), but aspart doses were higher (34 +/- 17 vs. 26 +/- 14 IU/day, P < 0.001) with once-daily detemir. At 7 months, A1C decreased slightly in patients switched from once-daily to twice-daily administration (8.2 +/- 0.8 vs. 8.0 +/- 0.8%; P = 0.34, NS) in association with increased total insulin doses (P < 0.05), but A1C increased in those switched from twice-daily to once-daily administration (7.2 +/- 0.9 vs. 7.6 +/- 0.8%, P < 0.05) in association with decreased doses (P < 0.05). Although some individuals may benefit from twice-daily dosing, the most suitable routine starting schedule for detemir in a basal-bolus regimen for type 1 diabetes is once-daily injection.Diabetes care 10/2008; 32(1):32-7. · 8.09 Impact Factor