Efficacy was analysed using mixed model repeated measures (MMRM), using observed cases (OC), with the baseline score as covariate, and country, sex, time (Months 1 6) and treatment as fixed effects; baseline score-by-time interaction and treatment-by-time interaction were also included in the model (see also: Gual et al., 2013; Mann et al., 2013).
For continuous endpoints efficacy was analysed using analysis of covariance, adjusting for RF status, geographical region and baseline value.
Treatment efficacies were analysed using the recommended WAAVP method and two open-source statistical procedures based on Bayesian modelling: 'eggCounts' and 'Bayescount'.
The primary efficacy variable was analysed using an analysis of covariance (ancova) model with treatment, cohort, ethnicity and interaction of treatment-by-ethnicity as fixed factors, and using baseline value as a covariate based on the PP population.
The primary efficacy end point was analysed using the primary analysis set, which consisted of the first 32 patients enrolled in phase II, all treated with a 16 mg m−2 dose of sagopilone.
The efficacy of third-line gefitinib was analysed using tumour response rates, time to third progression (TTTP), time to death (TTD) and changes in Karnofsky performance status (PS).
Methods were consistent with those of the EDITION studies and have been reported previously 3– 5. Change in HbA1c, and all other efficacy measures except insulin dose, was analysed using a mixed model for repeated measurements (MMRM).
For categorical endpoints, the efficacy of ofatumumab versus placebo was analysed using the Cochran Mantel Haenszel test, adjusting for baseline stratification factors, RF status and geographical region (ie, eastern Europe, western Europe, South America, Asia Pacific).
The effector cell-mediated cytotoxic efficacy of MT201 and trastuzumab was analysed using the panel of nine different human breast carcinoma cell lines of various antibody target antigen densities (Tables 1 and 2).
The efficacy of rituximab versus placebo was analysed using the Cochran Mantel–Haenszel test for categorical end points and analysis of variance (ANOVA) for continuous end points, adjusting for baseline stratification factors of rheumatoid factor (RF) status and region (USA vs non-USA).
The primary efficacy variable (trough FEV1 at week 12) was analysed using a mixed model, with treatment as a fixed effect and baseline FEV1 and FEV1 reversibility (in response to 80 μg ipratopium bromide), and baseline ICS use (yes/no) acting as covariates.
