Hal S. Stern

Bio: Hal S. Stern is an academic researcher from University of California, Irvine. The author has contributed to research in topics: Bayesian inference & Bayesian statistics. The author has an hindex of 42, co-authored 146 publications receiving 25831 citations. Previous affiliations of Hal S. Stern include Loma Linda University & Harvard University.

Logistic regression for empirical studies of multivariate selection

Abstract: Understanding the mechanics of adaptive evolution requires not only knowing the quantitative genetic bases of the traits of interest but also obtaining accurate measures of the strengths and modes of selection acting on these traits. Most recent empirical studies of multivariate selection have employed multiple linear regression to obtain estimates of the strength of selection. We reconsider the motivation for this approach, paying special attention to the effects of nonnormal traits and fitness measures. We apply an alternative statistical method, logistic regression, to estimate the strength of selection on multiple phenotypic traits. First, we argue that the logistic regression model is more suitable than linear regression for analyzing data from selection studies with dichotomous fitness outcomes. Subsequently, we show that estimates of selection obtained from the logistic regression analyses can be transformed easily to values that directly plug into equations describing adaptive microevolutionary change. Finally, we apply this methodology to two published datasets to demonstrate its utility. Because most statistical packages now provide options to conduct logistic regression analyses, we suggest that this approach should be widely adopted as an analytical tool for empirical studies of multivariate selection.

The relationship of respiratory and cardiovascular hospital admissions to the southern California wildfires of 2003.

Abstract: Objective There is limited information on the public health impact of wildfires. The relationship of cardiorespiratory hospital admissions (n = 40 856) to wildfire-related particulate matter (PM(2.5)) during catastrophic wildfires in southern California in October 2003 was evaluated. Methods Zip code level PM(2.5) concentrations were estimated using spatial interpolations from measured PM(2.5), light extinction, meteorological conditions, and smoke information from MODIS satellite images at 250 m resolution. Generalised estimating equations for Poisson data were used to assess the relationship between daily admissions and PM(2.5), adjusted for weather, fungal spores (associated with asthma), weekend, zip code-level population and sociodemographics. Results Associations of 2-day average PM(2.5) with respiratory admissions were stronger during than before or after the fires. Average increases of 70 microg/m(3) PM(2.5) during heavy smoke conditions compared with PM(2.5) in the pre-wildfire period were associated with 34% increases in asthma admissions. The strongest wildfire-related PM(2.5) associations were for people ages 65-99 years (10.1% increase per 10 microg/m(3) PM(2.5), 95% CI 3.0% to 17.8%) and ages 0-4 years (8.3%, 95% CI 2.2% to 14.9%) followed by ages 20-64 years (4.1%, 95% CI -0.5% to 9.0%). There were no PM(2.5)-asthma associations in children ages 5-18 years, although their admission rates significantly increased after the fires. Per 10 microg/m(3) wildfire-related PM(2.5), acute bronchitis admissions across all ages increased by 9.6% (95% CI 1.8% to 17.9%), chronic obstructive pulmonary disease admissions for ages 20-64 years by 6.9% (95% CI 0.9% to 13.1%), and pneumonia admissions for ages 5-18 years by 6.4% (95% CI -1.0% to 14.2%). Acute bronchitis and pneumonia admissions also increased after the fires. There was limited evidence of a small impact of wildfire-related PM(2.5) on cardiovascular admissions. Conclusions Wildfire-related PM(2.5) led to increased respiratory hospital admissions, especially asthma, suggesting that better preventive measures are required to reduce morbidity among vulnerable populations.

P50 sensory gating ratios in schizophrenics and controls: a review and data analysis.

Abstract: Many studies have found that the P50 sensory gating ratio in a paired click task is smaller in normal control subjects than in patients with schizophrenia, indicating more effective sensory gating. However, a wide range of gating ratios has been reported in the literature for both groups. The purpose of this study was to compile these findings and to compare reported P50 gating ratios in controls and patients with schizophrenia. Current data collected from individual controls in eight studies from the University of California, Irvine (UCI), Indiana University (IU), and Yale University also are reported. The IU, UCI, and Yale data showed that approximately 40% of controls had P50 ratios within 1 S.D. below the mean of means for patients with schizophrenia. The meta-analysis rejected the null hypothesis that all studies showed no effect. The meta-analysis also showed that the differences were not the same across all studies. The mean ratios in 45 of the 46 group comparisons were smaller for controls than for patients, and the observed difference in means was significant for 35 of those studies. Reported gating ratios for controls from two laboratories whose findings were reported in the literature differed from all the other control groups. Variables affecting the gating ratio included band pass filter setting, rules regarding the inclusion of P30, sex, and age. Standards of P50 collection and measurement would help determine whether the gating ratio can be sufficiently reliable to be labeled an endophenotype, and suggestions are made toward this goal.

Test–retest and between-site reliability in a multicenter fMRI study

Abstract: In the present report, estimates of test–retest and between‐site reliability of fMRI assessments were produced in the context of a multicenter fMRI reliability study (FBIRN Phase 1, http://www.nbirn.net). Five subjects were scanned on 10 MRI scanners on two occasions. The fMRI task was a simple block design sensorimotor task. The impulse response functions to the stimulation block were derived using an FIR‐deconvolution analysis with FMRISTAT. Six functionally‐derived ROIs covering the visual, auditory and motor cortices, created from a prior analysis, were used. Two dependent variables were compared: percent signal change and contrast‐to‐noise‐ratio. Reliability was assessed with intraclass correlation coefficients derived from a variance components analysis. Test–retest reliability was high, but initially, between‐site reliability was low, indicating a strong contribution from site and site‐by‐subject variance. However, a number of factors that can markedly improve between‐site reliability were uncovered, including increasing the size of the ROIs, adjusting for smoothness differences, and inclusion of additional runs. By employing multiple steps, between‐site reliability for 3T scanners was increased by 123%. Dropping one site at a time and assessing reliability can be a useful method of assessing the sensitivity of the results to particular sites. These findings should provide guidance toothers on the best practices for future multicenter studies. Hum Brain Mapp, 2008. © 2007 Wiley‐Liss, Inc.

Fragmentation and unpredictability of early-life experience in mental disorders.

Abstract: Maternal sensory signals in early life play a crucial role in programming the structure and function of the developing brain, promoting vulnerability or resilience to emotional and cognitive disorders. In rodent models of early-life stress, fragmentation and unpredictability of maternally derived sensory signals provoke persistent cognitive and emotional dysfunction in offspring. Similar variability and inconsistency of maternal signals during both gestation and early postnatal human life may influence development of emotional and cognitive functions, including those that underlie later depression and anxiety.

Fitting Linear Mixed-Effects Models Using lme4

Abstract: Maximum likelihood or restricted maximum likelihood (REML) estimates of the parameters in linear mixed-effects models can be determined using the lmer function in the lme4 package for R. As for most model-fitting functions in R, the model is described in an lmer call by a formula, in this case including both fixed- and random-effects terms. The formula and data together determine a numerical representation of the model from which the profiled deviance or the profiled REML criterion can be evaluated as a function of some of the model parameters. The appropriate criterion is optimized, using one of the constrained optimization functions in R, to provide the parameter estimates. We describe the structure of the model, the steps in evaluating the profiled deviance or REML criterion, and the structure of classes or types that represents such a model. Sufficient detail is included to allow specialization of these structures by users who wish to write functions to fit specialized linear mixed models, such as models incorporating pedigrees or smoothing splines, that are not easily expressible in the formula language used by lmer.

Latent dirichlet allocation

Abstract: We describe latent Dirichlet allocation (LDA), a generative probabilistic model for collections of discrete data such as text corpora. LDA is a three-level hierarchical Bayesian model, in which each item of a collection is modeled as a finite mixture over an underlying set of topics. Each topic is, in turn, modeled as an infinite mixture over an underlying set of topic probabilities. In the context of text modeling, the topic probabilities provide an explicit representation of a document. We present efficient approximate inference techniques based on variational methods and an EM algorithm for empirical Bayes parameter estimation. We report results in document modeling, text classification, and collaborative filtering, comparing to a mixture of unigrams model and the probabilistic LSI model.

Inference of population structure using multilocus genotype data

Abstract: We describe a model-based clustering method for using multilocus genotype data to infer population structure and assign individuals to populations. We assume a model in which there are K populations (where K may be unknown), each of which is characterized by a set of allele frequencies at each locus. Individuals in the sample are assigned (probabilistically) to populations, or jointly to two or more populations if their genotypes indicate that they are admixed. Our model does not assume a particular mutation process, and it can be applied to most of the commonly used genetic markers, provided that they are not closely linked. Applications of our method include demonstrating the presence of population structure, assigning individuals to populations, studying hybrid zones, and identifying migrants and admixed individuals. We show that the method can produce highly accurate assignments using modest numbers of loci— e.g. , seven microsatellite loci in an example using genotype data from an endangered bird species. The software used for this article is available from http://www.stats.ox.ac.uk/~pritch/home.html.

Latent Dirichlet Allocation

Abstract: We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI) [3]. In the context of text modeling, our model posits that each document is generated as a mixture of topics, where the continuous-valued mixture proportions are distributed as a latent Dirichlet random variable. Inference and learning are carried out efficiently via variational algorithms. We present empirical results on applications of this model to problems in text modeling, collaborative filtering, and text classification.

Fitting Linear Mixed-Effects Models using lme4

Abstract: Maximum likelihood or restricted maximum likelihood (REML) estimates of the parameters in linear mixed-effects models can be determined using the lmer function in the lme4 package for R. As for most model-fitting functions in R, the model is described in an lmer call by a formula, in this case including both fixed- and random-effects terms. The formula and data together determine a numerical representation of the model from which the profiled deviance or the profiled REML criterion can be evaluated as a function of some of the model parameters. The appropriate criterion is optimized, using one of the constrained optimization functions in R, to provide the parameter estimates. We describe the structure of the model, the steps in evaluating the profiled deviance or REML criterion, and the structure of classes or types that represents such a model. Sufficient detail is included to allow specialization of these structures by users who wish to write functions to fit specialized linear mixed models, such as models incorporating pedigrees or smoothing splines, that are not easily expressible in the formula language used by lmer.