Name: AndreaCappozzo
Type: User
Company: University of Milan
Bio: Assistant Professor in Statistics @ University of Milan.
Interests: Mixture models, Model-Based Clustering and Classification, Penalized estimation
Twitter: AndreaCappozzo
Location: Milan, Italy
Blog: https://andreacappozzo.rbind.io
AndreaCappozzo's Projects
Repo for academic style website
Public repo for BRAND: Bayesian Robust Adaptive Novelty Detector. A two-stage Bayesian Nonparametric model for novelty detection with robust prior information.
R package providing graphical and computational tools to guide parameter choice for the cluster weighted robust model. Associated paper Cappozzo, Garcìa Escudero, Greselin, Mayo-Iscar (2022+) Graphical and computational tools to guide parameter choice for the cluster weighted robust model.
R package for fitting penalised linear mixed-effect models via EM-type algorithms
"Building a package that lasts" — eRum 2018 workshop
e-Rum2020 program and materials
Public repository for the R package intRinsic
Nonparametric statistics POLIMI AY 2022/2023: lab notebooks
Multivariate Linear Sparse Group Lasso
:exclamation: This is a read-only mirror of the CRAN R package repository. MatTransMix — Clustering with Matrix Gaussian and Matrix Transformation Mixture Models
An R package for fitting high dimensional linear mixed-effects models with elastic-net penalty
:bar_chart: Generalized linear regression models with network-regularization in R.
:exclamation: This is a read-only mirror of the CRAN R package repository. parfm — Parametric Frailty Models
Quarto website
Model-based framework for robust classification that jointly accounts for outliers, label noise and unobserved classes in the test set.
R Interface to Python
Slide, code and data for "Applied Machine Learning" at Rstudio-conf 2018
Robust model-based classification based on trimming and constraints
This repository is associated with the paper Cappozzo, Garcìa Escudero, Greselin, Mayo-Iscar (2021) Parameter choice, stability and validity for robust cluster weighted modeling.
Trimmed Maximum Likelihood Estimation
Robust variable selection for REDDA models via EMST algorithm
Robust variable selection for REDDA models via TBIC approximation to the integrated likelihood. It is a robust adaptation of the greedy forward search algorithm for discriminant analysis. Based on clustvarsel R package.
Pretty timelines in R.