List of Figures
2.1 Distribution of the latent random variable vι ~ N(xtiβ, 1) according to Al-
bert and Chib’s model considering four categories, K = 3. The cutpoints Θ2
and Θ3 are random. The observed value ¾ is indicator of the interval where
Vi falls.................................... 15
2.2 Illustration of the distribution of the latent variable υiι in the model
described in (2.2)-(2.4) when the covariate takes values —1 and 1. Here
we consider: J — ∖ type of toxicity, no patient-specific random effect
ri, G = 2 components in the mixture of normals and three, K =
2, possible ordinal outcomes. In both mixtures, the darkly shaded,
lightly shaded and white areas correspond to the probabilities ττγι- of
the ordinal outcome taking the values 0, 1 and 2, respectively. .... 22
2.3 Boxplots of the simulated posterior samples of the ordinal probit model
parameters (χ3j,s). Boxes corresponding to samples of βj,s with 0.01-
quantile greater that zero are shaded................... 29
2.4 Estimated mixture of normal distribution of the latent variable vʊ
conditioned on η = 0 for j = 1,...,7. Shaded curve corresponds
to placebo (x = —1) and dashed to isotretinoin {x = 1). Darkly
and lightly shaded areas represent, respectively, the probability of no
toxicity (πjo) and toxicity at grade 1 (7r71) under placebo........ 30