Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data.
Ontology highlight
ABSTRACT:
SUBMITTER: Catav A
PROVIDER: S-EPMC8460841 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:During a pandemic, each country (or region) is characterized by a status matrix indicating its positive cases, hospitalizations and deaths. A pandemic performance indicator is a real-valued mapping from the set of status matrices to the set of non-negative real numbers, whereby lower values stand for better performance. We show that four axioms together characterize a family of indicators arising from a weighted average of the incidence rate, morbidity rate and mortality rate. We use these indicators to evaluate the impact of COVID-19 in major countries worldwide.
| S-EPMC9356370 | biostudies-literature
Project description:We study a marginal empirical likelihood approach in scenarios when the number of variables grows exponentially with the sample size. The marginal empirical likelihood ratios as functions of the parameters of interest are systematically examined, and we find that the marginal empirical likelihood ratio evaluated at zero can be used to differentiate whether an explanatory variable is contributing to a response variable or not. Based on this finding, we propose a unified feature screening procedure for linear models and the generalized linear models. Different from most existing feature screening approaches that rely on the magnitudes of some marginal estimators to identify true signals, the proposed screening approach is capable of further incorporating the level of uncertainties of such estimators. Such a merit inherits the self-studentization property of the empirical likelihood approach, and extends the insights of existing feature screening methods. Moreover, we show that our screening approach is less restrictive to distributional assumptions, and can be conveniently adapted to be applied in a broad range of scenarios such as models specified using general moment conditions. Our theoretical results and extensive numerical examples by simulations and data analysis demonstrate the merits of the marginal empirical likelihood approach.
| S-EPMC3887322 | biostudies-literature
Project description:The correlated-error ANOVA method proposed by Obuchowski and Rockette (OR) has been a useful procedure for analyzing reader-performance outcomes, such as the area under the receiver-operating-characteristic curve, resulting from multireader multicase radiological imaging data. This approach, however, has only been formally derived for the test-by-reader-by-case factorial study design. In this paper, I show that the OR model can be viewed as a marginal-mean ANOVA model. Viewing the OR model within this marginal-mean ANOVA framework is the basis for the marginal-mean ANOVA approach, the topic of this paper. This approach (1) provides an intuitive motivation for the OR model, including its covariance-parameter constraints; (2) provides easy derivations of OR test statistics and parameter estimates, as well as their distributions and confidence intervals; and (3) allows for easy generalization of the OR procedure to other study designs. In particular, I show how one can easily derive OR-type analysis formulas for any balanced study design by following an algorithm that only requires an understanding of conventional ANOVA methods.
| S-EPMC4640471 | biostudies-literature
Project description:PurposeCurrent limitations in methodologies used throughout machine-learning to investigate feature importance in boosted tree modelling prevent the effective scaling to datasets with a large number of features, particularly when one is investigating both the magnitude and directionality of various features on the classification into a positive or negative class. This manuscript presents a novel methodology, "Hollow-tree Super" (HOTS), designed to resolve and visualize feature importance in boosted tree models involving a large number of features. Further, this methodology allows for accurate investigation of the directionality and magnitude various features have on classification and incorporates cross-validation to improve the accuracy and validity of the determined features of importance.MethodsUsing the Iris dataset, we first highlight the characteristics of HOTS by comparing it to other commonly used techniques for feature importance, including Gini Importance, Partial Dependence Plots, and Permutation Importance, and explain how HOTS resolves the weaknesses present in these three strategies for investigating feature importance. We then demonstrate how HOTS can be utilized in high dimensional spaces such as neuroscientific setting, by taking 60 Schizophrenic subjects from the publicly available SchizConnect database and applying the method to determine which regions of the brain were most important for the positive and negative classification of schizophrenia as determined by the positive and negative syndrome scale (PANSS).ResultsHOTS effectively replicated and supported the findings of feature importance for classification of the Iris dataset when compared to Gini importance, Partial Dependence Plots and Permutation importance, determining 'petal length' as the most important feature for positive and negative classification. When applied to the Schizconnect dataset, HOTS was able to resolve from 379 independent features, the top 10 most important features for classification, as well as their directionality for classification and magnitude compared to other features. Cross-validation supported that these same 10 features were consistently used in the decision-making process across multiple trees, and these features were localised primarily to the occipital and parietal cortices, commonly disturbed brain regions in those afflicted with Schizophrenia.ConclusionHOTS effectively overcomes previous challenges of identifying feature importance at scale, and can be utilized across a swathe of disciplines. As computational power and data quantity continues to expand, it is imperative that a methodology is developed that is able to handle the demands of working with large datasets that contain a large number of features. This approach represents a unique way to investigate both the directionality and magnitude of feature importance when working at scale within a boosted tree model that can be easily visualized within commonly used software.
| S-EPMC8544862 | biostudies-literature
Project description:Metagenomics is revolutionizing our understanding of microbial communities, showing that their structure and composition have profound effects on the ecosystem and in a variety of health and disease conditions. Despite the flourishing of new analysis methods, current approaches based on statistical comparisons between high-level taxonomic classes often fail to identify the microbial taxa that are differentially distributed between sets of samples, since in many cases the taxonomic schema do not allow an adequate description of the structure of the microbiota. This constitutes a severe limitation to the use of metagenomic data in therapeutic and diagnostic applications. To provide a more robust statistical framework, we introduce a class of feature-weighting algorithms that discriminate the taxa responsible for the classification of metagenomic samples. The method unambiguously groups the relevant taxa into clades without relying on pre-defined taxonomic categories, thus including in the analysis also those sequences for which a taxonomic classification is difficult. The phylogenetic clades are weighted and ranked according to their abundance measuring their contribution to the differentiation of the classes of samples, and a criterion is provided to define a reduced set of most relevant clades. Applying the method to public datasets, we show that the data-driven definition of relevant phylogenetic clades accomplished by our ranking strategy identifies features in the samples that are lost if phylogenetic relationships are not considered, improving our ability to mine metagenomic datasets. Comparison with supervised classification methods currently used in metagenomic data analysis highlights the advantages of using phylogenetic information.
| S-EPMC4376673 | biostudies-literature
Project description:BackgroundMalnutrition among women disproportionately exists across socioeconomic classes of Bangladesh. According to our knowledge, studies which attempted to identify determinants and their contributions to explain BMI-based nutritional gap between the poorest and the richest categories of Wealth Index are still scarce.ObjectivesTo identify the nutritional gap of women between the richest-poorest classes in Bangladesh, and to determine how much of this gap are attributed to differences in predictors and differences in coefficients.Study populationReproductive-aged (15-49 years) women of Bangladesh.Methods and proceduresWe utilized the latest round (2017-2018) data of the Bangladesh Demographic and Health Survey (BDHS). Body mass index (BMI) has been used to measure the nutritional status of women. The kernel density was used to visualize the nutritional gap. The Oaxaca-Blinder (OB) decomposition method was used to ascertain influential determinants and their contributions to the existing gap between the richest-poorest classes of women.ResultsWe analyzed the data of 18,682 reproductive-aged women. There was a significant mean BMI gap of 4.1 unit (95% CI: 3.90-4.35) between the poorest-richest (25.6 vs 21.5) women. The overall prevalence of underweight, overweight and obese were 11.8%, 33.8% and 15.4%, respectively. The richest women were less underweight (7.5%) but more overweight (23.7%) and obese (42.2%). In contrast, the poorest women were more underweight (32.0%) but less overweight (13.9%) and obese (7.0%). According to results of OB decomposition method, all predictors combinedly can explain 1.62 units (95% CI: 1.31-1.93) of the total mean BMI gap (equivalent to 40%). Some of the major predictors were women years of education (0.45 units, 95% CI: 0.27-0.64), spouse years of education (0.16 units, 95% CI: -0.02-0.34), current working status (0.17 units, 95% CI: 0.10-0.34), access to Television (0.50 units, 95% CI: 0.28-0.72), and place of residence (0.37 units, 95% CI: 0.22-0.72). The unexplained part of the poorest-richest gap was 2.51 units (95% CI: 2.13-2.89), which means that this particular gap will remain unchanged even though the mean difference of the predictors was diminished.ConclusionsA large part of the nutritional gap (approximately 60%) between the poorest and richest classes of women are found to be unchanged by the predictors of the study. Therefore, further predictors should be identified to minimize such gap. Moreover, policy makers and relevant stakeholders should implement feasible strategies to minimize the existing differences in the major predictors.
| S-EPMC9436068 | biostudies-literature
Project description:A common two-tier structure for social networks is based on partitioning society into two parts, referred to as the elite and the periphery, where the "elite" is the relatively small but well-connected and highly influential group of powerful individuals around which the society is centered, and the "periphery" consists of the rest of society. It is observed that the relative sizes of economic and social elites in various societies appear to be continually declining. One possible explanation is that this is a natural social phenomenon, resembling Price's "square root" law for the fraction of good scientists in the scientific community. We try to assess the validity of this explanation by studying the elite-periphery structure via introducing a novel axiom-based model for representing and measuring the influence between the elite and the periphery. The model is accompanied by a set of axioms that capture the elite's dominance, robustness and density, as well as a compactness property. Relying on the model and the accompanying axioms, we are able to draw a number of insightful conclusions about the elite-periphery structure. In particular, we show that in social networks that respect our axioms, the size of a compact elite is sublinear in the network size. This agrees with Price's principle but appears to contradict the common belief that the elite size tends to a linear fraction of society (recently claimed to be around 1%). We propose a natural method to create partitions with nice properties, based on the key observation that an elite-periphery partition is at what we call a 'balance point', where the elite and the periphery maintain a balance of powers. Our method is based on setting the elite to be the k most influential nodes in the network and suggest the balance point as a tool for choosing k and therefore the size of the elite. When using nodes degrees to order the nodes, the resulting k-rich club at the balance point is the elite of a partition we refer to as the balanced edge-based partition. We accompany these findings with an empirical study on 32 real-world social networks, which provides evidence that balanced edge-based partitions which satisfying our axioms commonly exist.
| S-EPMC6200247 | biostudies-literature
Project description:BackgroundFeature selection, aiming to identify a subset of features among a possibly large set of features that are relevant for predicting a response, is an important preprocessing step in machine learning. In gene expression studies this is not a trivial task for several reasons, including potential temporal character of data. However, most feature selection approaches developed for microarray data cannot handle multivariate temporal data without previous data flattening, which results in loss of temporal information. We propose a temporal minimum redundancy - maximum relevance (TMRMR) feature selection approach, which is able to handle multivariate temporal data without previous data flattening. In the proposed approach we compute relevance of a gene by averaging F-statistic values calculated across individual time steps, and we compute redundancy between genes by using a dynamical time warping approach.ResultsThe proposed method is evaluated on three temporal gene expression datasets from human viral challenge studies. Obtained results show that the proposed method outperforms alternatives widely used in gene expression studies. In particular, the proposed method achieved improvement in accuracy in 34 out of 54 experiments, while the other methods outperformed it in no more than 4 experiments.ConclusionWe developed a filter-based feature selection method for temporal gene expression data based on maximum relevance and minimum redundancy criteria. The proposed method incorporates temporal information by combining relevance, which is calculated as an average F-statistic value across different time steps, with redundancy, which is calculated by employing dynamical time warping approach. As evident in our experiments, incorporating the temporal information into the feature selection process leads to selection of more discriminative features.
| S-EPMC5209828 | biostudies-literature
Project description:Multilevel functional data is collected in many biomedical studies. For example, in a study of the effect of Nimodipine on patients with subarachnoid hemorrhage (SAH), patients underwent multiple 4-hour treatment cycles. Within each treatment cycle, subjects' vital signs were reported every 10 minutes. This data has a natural multilevel structure with treatment cycles nested within subjects and measurements nested within cycles. Most literature on nonparametric analysis of such multilevel functional data focus on conditional approaches using functional mixed effects models. However, parameters obtained from the conditional models do not have direct interpretations as population average effects. When population effects are of interest, we may employ marginal regression models. In this work, we propose marginal approaches to fit multilevel functional data through penalized spline generalized estimating equation (penalized spline GEE). The procedure is effective for modeling multilevel correlated generalized outcomes as well as continuous outcomes without suffering from numerical difficulties. We provide a variance estimator robust to misspecification of correlation structure. We investigate the large sample properties of the penalized spline GEE estimator with multilevel continuous data and show that the asymptotics falls into two categories. In the small knots scenario, the estimated mean function is asymptotically efficient when the true correlation function is used and the asymptotic bias does not depend on the working correlation matrix. In the large knots scenario, both the asymptotic bias and variance depend on the working correlation. We propose a new method to select the smoothing parameter for penalized spline GEE based on an estimate of the asymptotic mean squared error (MSE). We conduct extensive simulation studies to examine property of the proposed estimator under different correlation structures and sensitivity of the variance estimation to the choice of smoothing parameter. Finally, we apply the methods to the SAH study to evaluate a recent debate on discontinuing the use of Nimodipine in the clinical community.
| S-EPMC3909538 | biostudies-literature
Project description:Tropical forests are important in worldwide carbon (C) storage and sequestration. C sequestration of these forests may especially be determined by the growth of canopy trees. However, the factors driving variation in growth among such large individuals remain largely unclear. We evaluate how crown traits [total leaf area, specific leaf area and leaf nitrogen (N) concentration] and stem traits [sapwood area (SA) and sapwood N concentration] measured for individual trees affect absolute biomass growth for 43 tropical canopy trees belonging to four species, in a moist forest in Bolivia. Biomass growth varied strongly among trees, between 17.3 and 367.3 kg year(-1), with an average of 105.4 kg year(-1). We found that variation in biomass growth was chiefly explained by a positive effect of SA, and not by tree size or other traits examined. SA itself was positively associated with sapwood growth, sapwood lifespan and basal area. We speculate that SA positively affects the growth of individual trees mainly by increasing water storage, thus securing water supply to the crown. These positive roles of sapwood on growth apparently offset the increased respiration costs incurred by more sapwood. This is one of the first individual-based studies to show that variation in sapwood traits-and not crown traits-explains variation in growth among tropical canopy trees. Accurate predictions of C dynamics in tropical forests require similar studies on biomass growth of individual trees as well as studies evaluating the dual effect of sapwood (water provision vs. respiratory costs) on tropical tree growth.
| S-EPMC4363484 | biostudies-literature