Learn R Programming

mixlink (version 0.1.5)

Find Vertices: Compute vertices for Mixture Link

Description

Find vertices of the set \(A(\vartheta, \bm{\pi})\), which characterizes link between finite mixture mean and regression function.

Usage

find.vertices.prob(mean, Pi, tol = 1e-08)

find.vertices.nonneg(mean, Pi)

Arguments

mean

Parameter \(\vartheta\) of distribution.

Pi

Parameter \(\bm{\pi}\) of distribution.

tol

A tolerance to determine if candidate vertices are distinct.

Value

A \(J \times k\) matrix whose columns are the vertices of \(A(\vartheta, \bm{\pi})\).

Details

For Mixture Link Binomial, the set \(A(\vartheta, \bm{\pi}) = \{ \bm{\mu} \in [0,1]^J : \bm{\mu}^T \bm{\pi} = \vartheta \}. \) For Mixture Link Poisson, the set \(A(\vartheta, \bm{\pi}) = \{ \bm{\mu} \in [0,\infty]^J : \bm{\mu}^T \bm{\pi} = \vartheta \}. \)

References

Andrew M. Raim, Nagaraj K. Neerchal, and Jorge G. Morel. An Extension of Generalized Linear Models to Finite Mixture Outcomes. arXiv preprint: 1612.03302