Robust Subgroup Identification

Zhang, Yingying; Wang, Huixia Judy; Zhu, Zhongyi

doi:10.5705/ss.202017.0179

Cited by 19 publications

(41 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been an active literature on panel data quantile regression, mainly focusing on estimation of the common parameters β(τ ) (e.g., Kato et al (2012), Galvao and Kato (2016), Harding and Lamarche (2017) and Galvao et al (2020)). Zhang et al (2019b) and Gu and Volgushev (2019) consider group structure on α i (τ ) ∈ R.…”

Section: Ifmentioning

confidence: 99%

Group structure estimation for panel data -- a general approach

Lei¹,

Gu²,

Volgushev³

2022

Preprint

View full text Add to dashboard Cite

Consider a panel data setting where repeated observations on individuals are available. Often it is reasonable to assume that there exist groups of individuals that share similar effects of observed characteristics, but the grouping is typically unknown in advance. We propose a novel approach to estimate such unobserved groupings for general panel data models. Our method explicitly accounts for the uncertainty in individual parameter estimates and remains computationally feasible with a large number of individuals and/or repeated measurements on each individual. The developed ideas can be applied even when individual-level data are not available and only parameter estimates together with some quantification of uncertainty are given to the researcher.

show abstract

Section: Ifmentioning

confidence: 99%

Group structure estimation for panel data -- a general approach

Lei¹,

Gu²,

Volgushev³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In the literature, a closely related line of research focuses on clustering with fusion penalties which apply to all the pairwise differences of centroids, and these methods are typically known as regression/fusion-based clustering methods, see for example, Pan et al (2013); Wu et al (2016); Zhang et al (2019). Regression/fusionbased clustering methods show an advantage in some complex clustering situations such as when non-convex clusters exist, in which traditional clustering methods K-means break down (Pan et al, 2013).…”

Section: Closely Related Literature Reviewmentioning

confidence: 99%

Simultaneous Cluster Structure Learning and Estimation of Heterogeneous Graphs for Matrix-variate fMRI Data

Liu¹,

Zhao²,

et al. 2021

Preprint

View full text Add to dashboard Cite

Graphical models play an important role in neuroscience studies, particularly in brain connectivity analysis. Typically, observations/samples are from several heterogenous groups and the group membership of each observation/sample is unavailable, which poses a great challenge for graph structure learning. In this article, we propose a method which can achieve Simultaneous Clustering and Estimation of Heterogeneous Graphs (briefly denoted as SCEHG) for matrix-variate function Magnetic Resonance Imaging (fMRI) data. Unlike the conventional clustering methods which rely on the mean differences of various groups, the proposed SCEHG method fully exploits the group differences of conditional dependence relationships among brain regions for learning cluster structure. In essence, by constructing individual-level between-region network measures, we formulate clustering as penalized regression with grouping and sparsity pursuit, which transforms the unsupervised learning into supervised learning. An ADMM algorithm is proposed to solve the corresponding optimization problem. We also propose a generalized criterion to specify the number of clusters. Extensive simulation studies illustrate the superiority of the SCEHG method over some state-of-the-art methods in terms of both clustering and graph recovery accuracy. We also apply the SCEHG procedure to analyze fMRI data associated with ADHD (abbreviated for Attention Deficit Hyperactivity Disorder), which illustrate its empirical usefulness. An R package "SCEHG" to implement the method is available at https://github.com/heyongstat/SCEHG.

show abstract

“…For example, Ma and Huang (2017) proposed a concave pairwise fusion learning method to identify subgroups whose heterogeneity is driven by unobserved latent factors and thus can be represented by subject-specific intercepts. Zhang et al (2019b) employed penalized median regression to detect subgroups automatically and achieve robustness against outliers and heteroscedasticity in random errors. Lu et al (2021) proposed a subgroup identification method based on concave fusion penalization and median regression for longitudinal data with dropouts.…”

Section: Introductionmentioning

confidence: 99%

Subgroup Analysis for Longitudinal data via Semiparametric Additive Mixed Effect Model

Bo¹,

Zhang²

2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose a general subgroup analysis framework based on semiparametric additive mixed effect models in longitudinal analysis, which can identify subgroups on each covariate and estimate the corresponding regression functions simultaneously. In addition, the proposed procedure is applicable for both balanced and unbalanced longitudinal data. A backfitting combined with k-means algorithm is developed to estimate each semiparametric additive component across subgroups and detect subgroup structure on each covariate respectively. The actual number of groups is estimated by minimizing a Bayesian information criteria. The numerical studies demonstrate the efficacy and accuracy of the proposed procedure in identifying the subgroups and estimating the regression functions. In addition, we illustrate the usefulness of our method with an application to PBC data and provide a meaningful partition of the population.

show abstract

Robust Subgroup Identification

Cited by 19 publications

References 25 publications

Group structure estimation for panel data -- a general approach

Group structure estimation for panel data -- a general approach

Simultaneous Cluster Structure Learning and Estimation of Heterogeneous Graphs for Matrix-variate fMRI Data

Subgroup Analysis for Longitudinal data via Semiparametric Additive Mixed Effect Model

Contact Info

Product

Resources

About