Edward L. Boone

Hypothesis testing and power calculations for taxonomic-based human microbiome data.

This paper presents new biostatistical methods for the analysis of microbiome data based on a fully parametric approach using all the data. The Dirichlet-multinomial distribution allows the analyst to calculate power and sample sizes for experimental design, perform tests of hypotheses (e.g., compare microbiomes across groups), and to estimate parameters describing microbiome properties. The use of a fully parametric model for these data has the benefit over alternative non-parametric approaches such as bootstrapping and permutation testing, in that this model is able to retain more information contained in the data. This paper details the statistical approaches for several tests of hypothesis and power/sample size calculations, and applies them for illustration to taxonomic abundance distribution and rank abundance distribution data using HMP Jumpstart data on 24 subjects for saliva, subgingival, and supragingival samples. Software for running these analyses is available.

Effects of age and composition of field-produced biofilms on oyster larval setting

Lack of success in restoring the native Eastern oyster, Crassostrea virginica, to Chesapeake Bay has been linked to the low occurrence of oyster larval setting in tributaries to the Bay. Among the many potential factors that could affect efforts to produce oysters through aquaculture or supplementation of shell beds is substratum condition. The present study examined larval setting on field-produced biofilms from Little Wicomico River (Virginia, USA) to assess whether bacterial community structure (examined by terminal restriction fragment length polymorphism, T-RFLP) or other characteristics of contemporary biofilms in this tributary (biofilm age and mass, algal abundance, and percentage organic matter) inhibited setting of larval oysters. The structure of the natural and heterogenous bacterial community in the biofilms and the success of oyster set were correlated, suggesting that specific microbial species may play a role in oyster setting. Larval set increased with biofilm age and mass, suggesting that established field-produced biofilms have no inhibitory effect. In contrast, the percentage of organic matter was negatively correlated with oyster set, whereas chlorophyll a concentration had no observed effect. The study expands prior knowledge by providing a more realistic timeframe for biofilm development (weeks as opposed to days), recounting effects of biofilms that are more representative of the natural dynamic and disturbance processes that would be expected to occur on submerged structures, and by incorporating seasonal and spatial variation. An important negative effect observed during the study period was heavy predation by Stylochus ellipticus on newly set oysters. Overall, the results of this study, which is the first assessment of the effects of biofilms produced naturally within a Chesapeake Bay tributary, suggest that the absence of large numbers of oysters in Little Wicomico River is not related to microbes or other specific characteristics of biofilms that develop on suitable setting substrata, but rather to heavy predation of newly set larvae.

Longitudinal changes in strength of police officers with gender comparisons.

Boyce, RW, Jones, GR, Schendt, KE, Lloyd, CL, and Boone, EL. Longitudinal changes in strength of police officers with gender comparisons. J Strength Cond Res 23(8): 2411-2418, 2009-Strength is a critical factor in the health and job performance of police officers. Using a retrospective longitudinal design, the purpose of this study was to identify differences in strength scores from initial recruitment to in-service tests and to compare gender differences. Strength changes were also compared in low- to high-strength groups. Strength scores included bench press, bench press/lean weight, and bench press/weight. Body weight, percent body fat, and bench press scores were retrieved for the 1990-1995 recruit classes and were paired to most recent scores on 2006 in-service fitness record. Sample included 327 police officers: 30 females and 297 males. Mean age at initial recruitment was 24.6 years and for in-service was 37.1 years. Average time between tests was 12.5 years. Over this period bench press and bench press/lean weight significantly increased for both gender groups (p ≤ 0.05). Bench press/weight remained relatively consistent. When dividing the mens strength scores into five low- to high-strength groups, there tended to be an averaging effect over time with the strongest group changing least and the weakest group changing most. In conclusion, the results of this study did not follow expected strength trends, which reported annual declines in muscular strength in men and women. Overall, officers increased in strength well into their late 30s. The practical applications of this study include documented benefits gained from maintaining ongoing fitness training and testing, as well as the potentially positive role of weight gain on strength. Also, low- to high-strength groups did not change relative positions over time even with improvements in strength scores, demonstrating the importance of minimum selection criteria for police.

A Hellinger distance approach to MCMC diagnostics

Bayesian analysis often requires the researcher to employ Markov Chain Monte Carlo (MCMC) techniques to draw samples from a posterior distribution which in turn is used to make inferences. Currently, several approaches to determine convergence of the chain as well as sensitivities of the resulting inferences have been developed. This work develops a Hellinger distance approach to MCMC diagnostics. An approximation to the Hellinger distance between two distributions f and g based on sampling is introduced. This approximation is studied via simulation to determine the accuracy. A criterion for using this Hellinger distance for determining chain convergence is proposed as well as a criterion for sensitivity studies. These criteria are illustrated using a dataset concerning the Anguilla australis, an eel native to New Zealand.

Age Estimation Using Thoracic and First Two Lumbar Vertebral Ring Epiphyseal Union

Abstract:  Union of the vertebral centra or “ring” epiphyses occurs during adolescence and early adulthood, providing valuable age at death information. We present a system for estimating age based on the timing and pattern of vertebral ring union. Data from 57 known individuals aged 14–27 years were used to establish age ranges for various patterns of union in females and males. Female age ranges were more well defined with less overlap in patterns of union than male age ranges. The age ranges are accompanied by descriptions of the stages of union observed that aid in applying this method. A test of interobserver error in scoring stages of union demonstrated strong consistency among three observers (r = 0.91–0.97). Estimating age by observing all stages documented resulted in 78%, 88%, and 100% accuracies using vertebral data alone. We encourage the continued use of this method, in conjunction with other age indicators.

Using data augmentation via the Gibbs Sampler to incorporate missing covariate structure in linear models for ecological assessments

Missing covariate values in linear regression models can be an important problem facing environmental researchers. Existing missing value treatment methods such as Multiple Imputation (MI), the EM algorithm and Data Augmentation (DA) have the assumption that both observed and unobserved data come from the same distribution, most commonly a multivariate normal or a conditionally multivariate normal family. These methods do try to incorporate the missing data mechanism and rely on the assumption of Missing At Random (MAR). We present a DA method which does not rely on the MAR assumption and can model missing data mechanisms and covariate structure. This method utilizes the Gibbs Sampler as a tool for incorporating these structures and mechanisms. We apply this method to an ecological data set that relates fish condition to environmental variables. Notice that the presented DA method detects relationships that are not detected when other missing data methods are employed.

Uncertainty Quantification for a Middle East Water Supply System

AbstractThis paper introduces a framework for incorporating uncertainty in water supply system models that uses Bayesian statistics and mixed-integer programming. The output of the framework includes the most probable least cost solution, the probability of feasibility for a given solution, component probabilities for each decision, and a distribution of the optimal objective function value. The method is applied to the problem of developing a water supply system design for Israel, Jordan, and the Palestinian territories. The method allows decision makers to evaluate various alternatives for a water supply plan that incorporates uncertainties in future demand and costs. The design of a water supply plan is a concern with properties that are distinct from traditional approaches to the design of water distribution systems; namely, local engineering decisions concerning pipe diameters and water pressure are not explicitly modeled, but large-scale decisions concerning the construction of water conveyances (pi...

Robust estimation and variable selection in sufficient dimension reduction

Dimension reduction and variable selection play important roles in high dimensional data analysis. Minimum Average Variance Estimation (MAVE) is an efficient approach among many others. However, because of the use of least squares criterion, MAVE is not robust to outliers in the dependent variable or errors with heavy tailed distributions. A robust extension of MAVE through modal regression is proposed. This new approach can adapt to different error distributions and thus brings robustness to the contamination in the response variable. The estimator is shown to have the same convergence rate as the original MAVE. Furthermore, the proposed method is combined with adaptive LASSO to select informative variables. The efficacy of this new solution is illustrated through simulation studies and a data analysis on Hong Kong air quality.

Bayesian hierarchical regression models for detecting QTLs in plant experiments

Quantitative trait loci (QTL) mapping is a growing field in statistical genetics. In plants, QTL detection experiments often feature replicates or clones within a specific genetic line. In this work, a Bayesian hierarchical regression model is applied to simulated QTL data and to a dataset from the Arabidopsis thaliana plants for locating the QTL mapping associated with cotyledon opening. A conditional model search strategy based on Bayesian model averaging is utilized to reduce the computational burden.

Spatial correlation matrix selection using Bayesian model averaging to characterize inter-tree competition in loblolly pine trees

Many applications of statistical methods for data that are spatially correlated require the researcher to specify the correlation structure of the data. This can be a difficult task as there are many candidate structures. Some spatial correlation structures depend on the distance between the observed data points while others rely on neighborhood structures. In this paper, Bayesian methods that systematically determine the ‘best’ correlation structure from a predefined class of structures are proposed. Bayes factors, Highest Probability Models, and Bayesian Model Averaging are employed to determine the ‘best’ correlation structure and to average across these structures to create a non-parametric alternative structure for a loblolly pine data-set with known tree coordinates. Tree diameters and heights were measured and an investigation into the spatial dependence between the trees was conducted. Results showed that the most probable model for the spatial correlation structure agreed with allometric trends for loblolly pine. A combined Matern, simultaneous autoregressive model and conditional autoregressive model best described the inter-tree competition among the loblolly pine tree data considered in this research.