Table 1.
Example extensions to the Hussey and Hughes model for stepped wedge cluster randomized trials in cross-sectional and closed-cohort designs; all models assume a continuous outcome and an identity link function.
| Design | Extension | Feature | Example references |
|---|---|---|---|
| Cross-sectional | Nested Exchangeable | Distinguish between within-period and between-period ICCs | Hooper et al.;56 Girling and Hemming38 |
| Exponential Decay | Allow the between-period ICC to decay at an exponential rate over time | Kasza et al.57 Kasza and Forbes61 | |
| Random Intervention | Include random cluster-specific intervention effects, and ICC depends on intervention status | Hughes et al.55 Hemming et al.47 | |
| Random Coefficient | Include random cluster-specific time slopes; ICC tends to be an increasing function of distance in time | Murray et al.58 | |
| Closed-cohort | Basic | Include cluster-level and subject-level random effects to separate between-individual ICC and within-individual ICC | Baio et al.65 |
| Block Exchangeable | Include three random effects to distinguish between within-period ICC, between-period ICC, and within-individual ICC | Hooper et al.56 Girling and Hemming38 | |
| Proportional Decay | Allow the between-period ICC and within-individual ICC to decay over time at the same exponential rate | Li60 | |
| Random Intervention | Include random cluster-specific intervention effects, and ICC depends on intervention status | Kasza et al.27 |
Note: The choice of terminology with the ‘*’ symbol is based on the following. The nested exchangeable correlation model was defined in Teerenstra et al.59 and Li et al.60 in the context of three-level CRTs and crossover CRTs. Li et al.34 introduced the block exchangeable correlation model for closed-cohort design and pointed out the nested exchangeable correlation model is a special case. The exponential decay correlation model is proposed in Kasza et al. and Kasza and Forbes.57,61 The proportional decay correlation model is introduced in Li60 and dates back to the earlier work of Liu et al.72 in the context of longitudinal parallel CRTs.