An S4 class to represent a multivariate diagonal Gaussian mixture model, extend icl_model-class
.
The model corresponds to the following generative model:
$$ \pi \sim Dirichlet(\alpha)$$
$$ Z_i \sim \mathcal{M}(1,\pi)$$
$$ \lambda_k^{(d)} \sim \mathcal{G}(\kappa,\beta)$$
$$ \mu_k^{(d)} \sim \mathcal{N}(\mu,(\tau \lambda_k)^{-1})$$
$$ X_{i.}|Z_{ik}=1 \sim \mathcal{N}(\mu_k,\lambda_{k}^{-1})$$
with \(\mathcal{G}(\kappa,\beta)\) the Gamma distribution with shape parameter \(\kappa\) and rate parameter \(\beta\).
name
name of the model
alpha
Dirichlet over cluster proportions prior parameter (default to 1)
tau
Prior parameter (inverse variance), (default 0.01)
kappa
Prior parameter (gamma shape), (default to 1)
beta
Prior parameter (gamma rate), (default to NaN, in this case beta will be estimated from data as 0.1 time the mean of X columns variances)
mu
Prior for the means (vector of size D), (default to NaN, in this case mu will be estimated from data as the mean of X)
Bertoletti, Marco & Friel, Nial & Rastelli, Riccardo. (2014). Choosing the number of clusters in a finite mixture model using an exact Integrated Completed Likelihood criterion. METRON. 73. 10.1007/s40300-015-0064-5. #'
new("diaggmm")#> An object of class "diaggmm" #> Slot "tau": #> [1] 0.01 #> #> Slot "kappa": #> [1] 1 #> #> Slot "beta": #> [1] NaN #> #> Slot "mu": #> [1] NaN #> #> Slot "name": #> [1] "diaggmm" #> #> Slot "alpha": #> [1] 1 #>new("diaggmm",alpha=1,tau=0.1,beta=0.1)#> An object of class "diaggmm" #> Slot "tau": #> [1] 0.1 #> #> Slot "kappa": #> [1] 1 #> #> Slot "beta": #> [1] 0.1 #> #> Slot "mu": #> [1] NaN #> #> Slot "name": #> [1] "diaggmm" #> #> Slot "alpha": #> [1] 1 #>