Regression with Highly Correlated Predictors: Variable Omission Is Not the Solution.
Ontology highlight
ABSTRACT:
SUBMITTER: Gregorich M
PROVIDER: S-EPMC8073086 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Statistical procedures for variable selection have become integral elements in any analysis. Successful procedures are characterized by high predictive accuracy, yielding interpretable models while retaining computational efficiency. Penalized methods that perform coefficient shrinkage have been shown to be successful in many cases. Models with correlated predictors are particularly challenging to tackle. We propose a penalization procedure that performs variable selection while clustering groups of predictors automatically. The oracle properties of this procedure including consistency in group identification are also studied. The proposed method compares favorably with existing selection approaches in both prediction accuracy and model discovery, while retaining its computational efficiency. Supplemental material are available online.
| S-EPMC3678393 | biostudies-literature
Project description:In this work, we develop a Bayesian approach to perform selection of predictors that are linked within a network. We achieve this by combining a sparse regression model relating the predictors to a response variable with a graphical model describing conditional dependencies among the predictors. The proposed method is well-suited for genomic applications because it allows the identification of pathways of functionally related genes or proteins that impact an outcome of interest. In contrast to previous approaches for network-guided variable selection, we infer the network among predictors using a Gaussian graphical model and do not assume that network information is available a priori. We demonstrate that our method outperforms existing methods in identifying network-structured predictors in simulation settings and illustrate our proposed model with an application to inference of proteins relevant to glioblastoma survival.
| S-EPMC4775388 | biostudies-literature
Project description:Eelgrass (Zostera marina) is a marine foundation species essential for coastal ecosystem services around the northern hemisphere. Like all macroscopic organisms, it possesses a microbiome (here defined as an associated prokaryotic community) which may play critical roles in modulating the interaction of eelgrass with its environment. For example, its leaf surface microbiome could inhibit or attract eukaryotic epibionts which may overgrow the eelgrass leading to reduced primary productivity and subsequent eelgrass meadow decline. We used amplicon sequencing of the 16S and 18S rRNA genes of prokaryotes and eukaryotes to assess the leaf surface microbiome (prokaryotes) as well as eukaryotic epibionts in- and outside lagoons on the German Baltic Sea coast. Prokaryote microbiomes varied substantially both between sites inside lagoons and between open coastal and lagoon sites. Water depth, leaf area and biofilm chlorophyll a concentration explained a large amount of variation in both prokaryotic and eukaryotic community composition. The prokaryotic microbiome and eukaryotic epibiont communities were highly correlated, and network analysis revealed disproportionate co-occurrence between a limited number of eukaryotic taxa and several bacterial taxa. This suggests that eelgrass leaf surfaces are home to a mosaic of microbiomes of several epibiotic eukaryotes, in addition to the microbiome of the eelgrass itself. Our findings thereby underline that eukaryotic diversity should be taken into account in order to explain prokaryotic microbiome assembly and dynamics in aquatic environments.
| S-EPMC5507959 | biostudies-literature
Project description:Concern over rapid environmental shifts associated with climate change has led to a search for molecular markers of environmental tolerance. Climate-associated gene expression profiles exist for a number of systems, but have rarely been tied to fitness outcomes, especially in nonmodel organisms. We reciprocally transplanted corals between two backreef locations with more and less variable temperature regimes to disentangle effects of recent and native environment on survival and growth. Coral growth over 12 months was largely determined by local environment. Survival, however, was impacted by native environment; corals from the more variable environment had 22% higher survivorship. By contrast, corals native to the less variable environment had more variable survival. This might represent a "selective sieve" where poor survivors are filtered from the more stressful environment. We also find a potential fitness trade-off-corals with high survival under stressful conditions grew less in the more benign environment. Transcriptome samples taken a year before transplantation were used to examine gene expression patterns that predicted transplant survival and growth. Two separate clusters of coexpressed genes were predictive of survival in the two locations. Genes from these clusters are candidate biomarkers for predicting persistence of corals under future climate change scenarios.
| S-EPMC5496549 | biostudies-literature
Project description:Alterations in DNA methylation in cancer include global hypomethylation and gene-specific hypermethylation. It is not clear whether these two epigenetic errors are mechanistically linked or occur independently. This study was performed to determine the relationship between DNA hypomethylation, hypermethylation and microsatellite instability in cancer.We examined 61 cancer cell lines and 60 colorectal carcinomas and their adjacent tissues using LINE-1 bisulfite-PCR as a surrogate for global demethylation. Colorectal carcinomas with sporadic microsatellite instability (MSI), most of which are due to a CpG island methylation phenotype (CIMP) and associated MLH1 promoter methylation, showed in average no difference in LINE-1 methylation between normal adjacent and cancer tissues. Interestingly, some tumor samples in this group showed increase in LINE-1 methylation. In contrast, MSI-showed a significant decrease in LINE-1 methylation between normal adjacent and cancer tissues (P<0.001). Microarray analysis of repetitive element methylation confirmed this observation and showed a high degree of variability in hypomethylation between samples. Additionally, unsupervised hierarchical clustering identified a group of highly hypomethylated tumors, composed mostly of tumors without microsatellite instability. We extended LINE-1 analysis to cancer cell lines from different tissues and found that 50/61 were hypomethylated compared to peripheral blood lymphocytes and normal colon mucosa. Interestingly, these cancer cell lines also exhibited a large variation in demethylation, which was tissue-specific and thus unlikely to be resultant from a stochastic process.Global hypomethylation is partially reversed in cancers with microsatellite instability and also shows high variability in cancer, which may reflect alternative progression pathways in cancer.
| S-EPMC1851990 | biostudies-literature
Project description:In risk evaluation, the effect of mixtures of environmental chemicals on a common adverse outcome is of interest. However, due to the high dimensionality and inherent correlations among chemicals that occur together, the traditional methods (e.g. ordinary or logistic regression) suffer from collinearity and variance inflation, and shrinkage methods have limitations in selecting among correlated components. We propose a weighted quantile sum (WQS) approach to estimating a body burden index, which identifies "bad actors" in a set of highly correlated environmental chemicals. We evaluate and characterize the accuracy of WQS regression in variable selection through extensive simulation studies through sensitivity and specificity (i.e., ability of the WQS method to select the bad actors correctly and not incorrect ones). We demonstrate the improvement in accuracy this method provides over traditional ordinary regression and shrinkage methods (lasso, adaptive lasso, and elastic net). Results from simulations demonstrate that WQS regression is accurate under some environmentally relevant conditions, but its accuracy decreases for a fixed correlation pattern as the association with a response variable diminishes. Nonzero weights (i.e., weights exceeding a selection threshold parameter) may be used to identify bad actors; however, components within a cluster of highly correlated active components tend to have lower weights, with the sum of their weights representative of the set.
| S-EPMC6261506 | biostudies-literature
Project description:BackgroundFor many practical hypothesis testing (H-T) applications, the data are correlated and/or with heterogeneous variance structure. The regression t-test for weighted linear mixed-effects regression (LMER) is a legitimate choice because it accounts for complex covariance structure; however, high computational costs and occasional convergence issues make it impractical for analyzing high-throughput data. In this paper, we propose computationally efficient parametric and semiparametric tests based on a set of specialized matrix techniques dubbed as the PB-transformation. The PB-transformation has two advantages: 1. The PB-transformed data will have a scalar variance-covariance matrix. 2. The original H-T problem will be reduced to an equivalent one-sample H-T problem. The transformed problem can then be approached by either the one-sample Student's t-test or Wilcoxon signed rank test.ResultsIn simulation studies, the proposed methods outperform commonly used alternative methods under both normal and double exponential distributions. In particular, the PB-transformed t-test produces notably better results than the weighted LMER test, especially in the high correlation case, using only a small fraction of computational cost (3 versus 933 s). We apply these two methods to a set of RNA-seq gene expression data collected in a breast cancer study. Pathway analyses show that the PB-transformed t-test reveals more biologically relevant findings in relation to breast cancer than the weighted LMER test.ConclusionsAs fast and numerically stable replacements for the weighted LMER test, the PB-transformed tests are especially suitable for "messy" high-throughput data that include both independent and matched/repeated samples. By using our method, the practitioners no longer have to choose between using partial data (applying paired tests to only the matched samples) or ignoring the correlation in the data (applying two sample tests to data with some correlated samples). Our method is implemented as an R package 'PBtest' and is available at https://github.com/yunzhang813/PBtest-R-Package .
| S-EPMC6466736 | biostudies-literature
Project description:Regression models are introduced into the receiver operating characteristic (ROC) analysis to accommodate effects of covariates, such as genes. If many covariates are available, the variable selection issue arises. The traditional induced methodology separately models outcomes of diseased and nondiseased groups; thus, separate application of variable selections to two models will bring barriers in interpretation, due to differences in selected models. Furthermore, in the ROC regression, the accuracy of area under the curve (AUC) should be the focus instead of aiming at the consistency of model selection or the good prediction performance. In this paper, we obtain one single objective function with the group SCAD to select grouped variables, which adapts to popular criteria of model selection, and propose a two-stage framework to apply the focused information criterion (FIC). Some asymptotic properties of the proposed methods are derived. Simulation studies show that the grouped variable selection is superior to separate model selections. Furthermore, the FIC improves the accuracy of the estimated AUC compared with other criteria.
| S-EPMC3838845 | biostudies-other
Project description:BACKGROUND: In addition to sequence conservation, protein multiple sequence alignments contain evolutionary signal in the form of correlated variation among amino acid positions. This signal indicates positions in the sequence that influence each other, and can be applied for the prediction of intra- or intermolecular contacts. Although various approaches exist for the detection of such correlated mutations, in general these methods utilize only pairwise correlations. Hence, they tend to conflate direct and indirect dependencies. RESULTS: We propose RMRCM, a method for Regularized Multinomial Regression in order to obtain Correlated Mutations from protein multiple sequence alignments. Importantly, our method is not restricted to pairwise (column-column) comparisons only, but takes into account the network nature of relationships between protein residues in order to predict residue-residue contacts. The use of regularization ensures that the number of predicted links between columns in the multiple sequence alignment remains limited, preventing overprediction. Using simulated datasets we analyzed the performance of our approach in predicting residue-residue contacts, and studied how it is influenced by various types of noise. For various biological datasets, validation with protein structure data indicates a good performance of the proposed algorithm for the prediction of residue-residue contacts, in comparison to previous results. RMRCM can also be applied to predict interactions (in addition to only predicting interaction sites or contact sites), as demonstrated by predicting PDZ-peptide interactions. CONCLUSIONS: A novel method is presented, which uses regularized multinomial regression in order to obtain correlated mutations from protein multiple sequence alignments. AVAILABILITY: R-code of our implementation is available via http://www.ab.wur.nl/rmrcm.
| S-EPMC3247924 | biostudies-literature
Project description:We propose a new method for regression using a parsimonious and scientifically interpretable representation of functional predictors. Our approach is designed for data that exhibit features such as spikes, dips, and plateaus whose frequency, location, size, and shape varies stochastically across subjects. We propose Bayesian inference of the joint functional and exposure models, and give a method for efficient computation. We contrast our approach with existing state-of-the-art methods for regression with functional predictors, and show that our method is more effective and efficient for data that include features occurring at varying locations. We apply our methodology to a large and complex dataset from the Sleep Heart Health Study, to quantify the association between sleep characteristics and health outcomes. Software and technical appendices are provided in online supplemental materials.
| S-EPMC3842620 | biostudies-literature