Dataset Information

Can longitudinal generalized estimating equation models distinguish network influence and homophily? An agent-based modeling approach to measurement characteristics.

ABSTRACT: BACKGROUND:Connected individuals (or nodes) in a network are more likely to be similar than two randomly selected nodes due to homophily and/or network influence. Distinguishing between these two influences is an important goal in network analysis, and generalized estimating equation (GEE) analyses of longitudinal dyadic network data are an attractive approach. It is not known to what extent such regressions can accurately extract underlying data generating processes. Therefore our primary objective is to determine to what extent, and under what conditions, does the GEE-approach recreate the actual dynamics in an agent-based model. METHODS:We generated simulated cohorts with pre-specified network characteristics and attachments in both static and dynamic networks, and we varied the presence of homophily and network influence. We then used statistical regression and examined the GEE model performance in each cohort to determine whether the model was able to detect the presence of homophily and network influence. RESULTS:In cohorts with both static and dynamic networks, we find that the GEE models have excellent sensitivity and reasonable specificity for determining the presence or absence of network influence, but little ability to distinguish whether or not homophily is present. CONCLUSIONS:The GEE models are a valuable tool to examine for the presence of network influence in longitudinal data, but are quite limited with respect to homophily.

SUBMITTER: Sauser Zachrison K

PROVIDER: S-EPMC5192582 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Can longitudinal generalized estimating equation models distinguish network influence and homophily? An agent-based modeling approach to measurement characteristics.

Sauser Zachrison Kori K Iwashyna Theodore J TJ Gebremariam Achamyeleh A Hutchins Meghan M Lee Joyce M JM

BMC medical research methodology 20161228 1

<h4>Background</h4>Connected individuals (or nodes) in a network are more likely to be similar than two randomly selected nodes due to homophily and/or network influence. Distinguishing between these two influences is an important goal in network analysis, and generalized estimating equation (GEE) analyses of longitudinal dyadic network data are an attractive approach. It is not known to what extent such regressions can accurately extract underlying data generating processes. Therefore our prima ...[more]

PMID: 28031023

Similar Datasets

Project description:BackgroundEvent-related potentials (ERP) data are widely used in brain studies that measure brain responses to specific stimuli using electroencephalogram (EEG) with multiple electrodes. Previous ERP data analyses haven't accounted for the structured correlation among observations in ERP data from multiple electrodes, and therefore ignored the electrode-specific information and variation among the electrodes on the scalp. Our objective was to evaluate the impact of early adversity on brain connectivity by identifying risk factors and early-stage biomarkers associated with the ERP responses while properly accounting for structured correlation.MethodsIn this study, we extend a penalized generalized estimating equation (PGEE) method to accommodate structured correlation of ERPs that accounts for electrode-specific data and to enable group selection, such that grouped covariates can be evaluated together for their association with brain development in a birth cohort of urban-dwelling Bangladeshi children. The primary ERP responses of interest in our study are N290 amplitude and the difference in N290 amplitude.ResultsThe selected early-stage biomarkers associated with the N290 responses are representatives of enteric inflammation (days of diarrhea, MIP1b, retinol binding protein (RBP), Zinc, myeloperoxidase (MPO), calprotectin, and neopterin), systemic inflammation (IL-5, IL-10, ferritin, C Reactive Protein (CRP)), socioeconomic status (household expenditure), maternal health (mother height) and sanitation (water treatment).ConclusionsOur proposed group penalized GEE estimator with structured correlation matrix can properly model the complex ERP data and simultaneously identify informative biomarkers associated with such brain connectivity. The selected early-stage biomarkers offer a potential explanation for the adversity of neurocognitive development in low-income countries and facilitate early identification of infants at risk, as well as potential pathways for intervention.Trial registrationThe related clinical study was retrospectively registered with https://doi.org/ClinicalTrials.gov , identifier NCT01375647, on June 3, 2011.

Project description:The relationship between the human gut microbiota and disease is of increasing scientific interest. Previous investigations have focused on the differences in intestinal bacterial abundance between control and affected groups to identify disease biomarkers. However, different types of intestinal bacteria may have interacting effects and thus be considered biomarker complexes for disease. To investigate this, we aimed to identify a new kind of biomarker for atopic dermatitis using structural equation modeling (SEM). The biomarkers identified were latent variables, which are complex and derived from the abundance data for bacterial marker candidates. Groups of females and males classified as healthy participants [normal control (NC) (female: 321 participants, male: 99 participants)], and patients afflicted with atopic dermatitis only [AS (female: 45 participants, male: 13 participants)], with atopic dermatitis and other diseases [AM (female: 75 participants, male: 34 participants)], and with other diseases but without atopic dermatitis [OD (female: 1,669 participants, male: 866 participants)] were used in this investigation. The candidate bacterial markers were identified by comparing the intestinal microbial community compositions between the NC and AS groups. In females, two latent variables (lv) were identified; for lv1, the associated components (bacterial genera) were Alistipes, Butyricimonas, and Coprobacter, while for lv2, the associated components were Agathobacter, Fusicatenibacter, and Streptococcus. There was a significant difference in the lv2 scores between the groups with atopic dermatitis (AS, AM) and those without (NC, OD), and the genera identified for lv2 are associated with the suppression of inflammatory responses in the body. A logistic regression model to estimate the probability of atopic dermatitis morbidity with lv2 as an explanatory variable had an area under the curve (AUC) score of 0.66 when assessed using receiver operating characteristic (ROC) analysis, and this was higher than that using other logistic regression models. The results indicate that the latent variables, especially lv2, could represent the effects of atopic dermatitis on the intestinal microbiome in females. The latent variables in the SEM could thus be utilized as a new type of biomarker. The advantages identified for the SEM are as follows: (1) it enables the extraction of more sophisticated information when compared with models focused on individual bacteria and (2) it can improve the accuracy of the latent variables used as biomarkers, as the SEM can be expanded.

Dataset Information

Can longitudinal generalized estimating equation models distinguish network influence and homophily? An agent-based modeling approach to measurement characteristics.

Publications

Can longitudinal generalized estimating equation models distinguish network influence and homophily? An agent-based modeling approach to measurement characteristics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets