eldorado.tu-dortmund.de/server/api/core/bitstreams/5ed0a0f9-f0af-4123-8183-b9ad2697b5fe/content
Subgroup analyses and investigations of treatment effect heterogeneity in clinical dose-finding tria
β1d+ β2d 2 d+ (β2/|β1|)d2
Beta E0 + EmaxB(δ1, δ2)(δ/D)δ1(1− d/D)δ2 (δ/D)δ1(1− d/D)δ2
Table 3.1: Common dose response-models and their standardized form (from Xun and
Bretz (2017)). Here B(δ1, δ2) = (δ1 [...] in Biopharmaceutical Research,
9 (2), 160–171
As discussed in Section 2.1.2 in Chapter 2 subgroups are in practice often analyzed using
univariate models of type (2.2) and by testing for significant i [...] dose-response models have horsehoe
priors
βj ∼ N(0, τ 2βλ (prog) j
2 ), j = 1, . . . , k
γj ∼ N(0, τ 2γλ (pred) j
2 ), j = 1, . . . , k
δj ∼ N(0, τ 2δ λ (pred) j
2 ), j = 1, . . . , k.
(4.3)
The prior variance …
