Multivariate Analysis of Mixed Data: The R Package PCAmixdata

Chavent, Marie; Kuentz-Simonet, Vanessa; Labenne, Amaury; Saracco, Jérôme

doi:10.48550/arxiv.1411.4911

Cited by 25 publications

(25 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To account for the fact that we have both noncategorical and categorical SES indicators, we used a method that is often called factorial analysis of mixed data, which is essentially a generalization of PCA that can handle such mixed data (45,46). This method combines ordinary PCA for noncategorical data with multiple correspondence analysis for categorical data and is implemented in the R package PCAmix (47).…”

Section: Ses Measuresmentioning

confidence: 99%

Human brain anatomy reflects separable genetic and environmental components of socioeconomic status

et al. 2022

View full text Add to dashboard Cite

Socioeconomic status (SES) correlates with brain structure, a relation of interest given the long-observed relations of SES to cognitive abilities and health. Yet, major questions remain open, in particular, the pattern of causality that underlies this relation. In an unprecedently large study, here, we assess genetic and environmental contributions to SES differences in neuroanatomy. We first establish robust SES–gray matter relations across a number of brain regions, cortical and subcortical. These regional correlates are parsed into predominantly genetic factors and those potentially due to the environment. We show that genetic effects are stronger in some areas (prefrontal cortex, insula) than others. In areas showing less genetic effect (cerebellum, lateral temporal), environmental factors are likely to be influential. Our results imply a complex interplay of genetic and environmental factors that influence the SES-brain relation and may eventually provide insights relevant to policy.

show abstract

Section: Ses Measuresmentioning

confidence: 99%

Human brain anatomy reflects separable genetic and environmental components of socioeconomic status

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Considering the potential bias on datasets, phylogenetic reconstruction of the Cactaceae tree was performed using three datasets with distinct amounts of missing data (MD; 40%, 60%, and 80%; supplementary material). We compared the phylogenetic tree topologies with the symmetric Robinson-Foulds (RF) pairwise distance (Robinson and Foulds, 1981) in the R package phytools (Revel, 2012) and performed a Principal Coordinate Analysis (PCoA) in the R package PCAmixdata (Chavent et al, 2017). We also conducted experimental pilots using the three MD datasets and observed a similar diversity pattern, except for the 40% MD dataset, which was an outlier in PCA, showed shorter branches, and displayed the highest level of PD.…”

Section: 2molecular Data and Phylogenetic Analysismentioning

confidence: 99%

Spatial patterns of evolutionary diversity in Cactaceae show low ecological representation within protected areas

Amaral

Bonatelli

Romeiro-Brito

et al. 2022

Preprint

View full text Add to dashboard Cite

Mapping biodiversity patterns across taxa and environments is crucial to address the evolutionary and ecological dimensions of species distribution, suggesting areas of particular importance for conservation purposes. Within Cactaceae, spatial diversity patterns are poorly explored, as well as the abiotic factors that may predict these patterns. We gathered geographic and genetic data from 922 cactus species, which are tightly associated with drylands, to evaluate diversity patterns, such as phylogenetic diversity and endemism, paleo-, neo-, and superendemism, and the environmental predictor variables of such patterns in a global analysis. Hotspot areas of cacti diversity are scattered along the Neotropical and Nearctic regions, mainly in the desertic portion of Mesoamerica, Caribbean Island, and the dry diagonal of South America. The geomorphological features of these regions may create a complexity of areas that work as locally buffered zones over time, which triggers local events of diversification and speciation. Desert and dryland/dry forest areas comprise paleo- and superendemism and may act as both museums and cradles of species, displaying great importance for conservation. Past climates, topography, soil features, and solar irradiance seem to be the main predictors of distinct endemism types. The hotspot areas that encompass a major part of the endemism cells are outside or poorly covered by formal protection units. The current legally protected areas are not able to conserve cactus evolutionary history. Given the rapid anthropogenic disturbance, efforts must be reinforced to monitor biodiversity and the environment and to define/plan current and new protected areas.

show abstract

“…However, this method can be sensitive to outliers and ignores important multivariate data features. An alternative approach is to apply a dimensionality reduction technique on mixed data, such as unimodal Variational Autoencoder (Simidjievski et al, 2019), Factor Analysis of Mixed Data (FAMD) (Pagès, 2021), or PCA for mixed data (PCAmix) (Chavent et al, 2014). An alternative regime is to operate in segmented datasets using methods such as subspace clustering and multi-view clustering.…”

Section: Mixed and Multimodal Datamentioning

confidence: 99%

Evaluating individual heterogeneity in mental health research: an overview of clustering methods and guidelines for applications

Gao¹,

Dwyer²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Clustering models or cluster analyses have been widely used to explore individual heterogeneity in mental health research. Despite advances in new algorithms and increasing popularity, there is little guidance on model choice, analytical framework and reporting requirements when using clustering models. In this review, we first provided a comprehensive introduction to the philosophy, design and implementation of major algorithms that are particularly relevant in mental health research. The design, comparisons and implementations (in R package) of different models and dissimilarity measures are discussed. The extensions of basic models, such as kernel method, deep learning, semi-supervised clustering, and clustering ensembles were subsequently introduced. Methods for pre-clustering data processing, clustering evaluation and validation, as well as important issues commonly faced in clustering tasks are discussed. Importantly, we provided general guidance on clustering workflow and reporting requirements. A rapid review of publications (December 2020-December 2021) was conducted focusing on the top six psychology and psychiatry journals that published most of the clustering papers. The results have highlighted that there was a lack of diversity in the algorithm of choice, robust validation processes via resampling, and available data and analysis code to improve reproducibility. This comprehensive review offers researchers advanced tools and guidelines to address some of these issues, improve practice and ultimately understanding of the complexity of mental illness.

show abstract

Multivariate Analysis of Mixed Data: The R Package PCAmixdata

Cited by 25 publications

References 9 publications

Human brain anatomy reflects separable genetic and environmental components of socioeconomic status

Human brain anatomy reflects separable genetic and environmental components of socioeconomic status

Spatial patterns of evolutionary diversity in Cactaceae show low ecological representation within protected areas

Evaluating individual heterogeneity in mental health research: an overview of clustering methods and guidelines for applications

Contact Info

Product

Resources

About