2019
DOI: 10.1093/biomet/asz064
|View full text |Cite
|
Sign up to set email alerts
|

A conditional density estimation partition model using logistic Gaussian processes

Abstract: Conditional density estimation (density regression) estimates the distribution of a response variable y conditional on covariates x. Utilizing a partition model framework, a conditional density estimation method is proposed using logistic Gaussian processes. The partition is created using a Voronoi tessellation and is learned from the data using a reversible jump Markov chain Monte Carlo algorithm. The Markov chain Monte Carlo algorithm is made possible through a Laplace approximation on the latent variables o… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 46 publications
0
3
0
Order By: Relevance
“…An important direction for future research is to extend the proposed Bayesian sum of trees model to accommodate additional data features commonly encountered in practice, such as time‐ and covariate‐dependent time series (Bertolacci et al., 2022), extra spectral variability due to clustering effects (Krafty, 2016), and missingness in covariate vectors. Alternative partitioning frameworks, such Voronoi tessellations (Payne et al., 2020) and binary space partitioning trees (Fan et al., 2019), and soft‐decision trees (Linero & Yang, 2018) that better adapt to smooth effects may also be considered for capturing covariate effects in an even more flexible and parsimonious manner.…”
Section: Discussionmentioning
confidence: 99%
“…An important direction for future research is to extend the proposed Bayesian sum of trees model to accommodate additional data features commonly encountered in practice, such as time‐ and covariate‐dependent time series (Bertolacci et al., 2022), extra spectral variability due to clustering effects (Krafty, 2016), and missingness in covariate vectors. Alternative partitioning frameworks, such Voronoi tessellations (Payne et al., 2020) and binary space partitioning trees (Fan et al., 2019), and soft‐decision trees (Linero & Yang, 2018) that better adapt to smooth effects may also be considered for capturing covariate effects in an even more flexible and parsimonious manner.…”
Section: Discussionmentioning
confidence: 99%
“…An important direction for future research is to extend the proposed Bayesian sum of trees model to accommodate additional data features commonly encountered in practice, such as time-and covariate-dependent time series (Bertolacci et al, 2019), extra spectral variability due to clustering effects (Krafty, 2016), and missingness in covariate vectors. Alternative partitioning frameworks, such Voronoi tesselations (Payne et al, 2020) and binary space partitioning trees (Fan et al, 2019), may also be considered for capturing covariate effects in an even more flexible and parsimonious manner.…”
Section: Discussionmentioning
confidence: 99%
“…The statistics literature on univariate density estimation is enormous; and the problem of covariate density estimation, sometimes referred to as density regression, has also received attention (see, e.g., Payne et al, 2020, and the references therein). The literature on multivariate density estimation, in contrast, is small and the literature on multivariate density regression almost non-existent.…”
Section: Supplementary Materials Formentioning
confidence: 99%