Search

In this paper we introduce a new procedure for spatial sampling design. It is found in previous studies (Zhu and Stein in J Agric Biol Environ Stat 11:24–44, 2006) that the optimal sampling design for spatial prediction with estimated parameters is nearly regular with a few clustered points. The pattern is similar to a generalization of the Neyman–Scott (GNS) process (Yau and Loh in Statistica Sinica 22:1717–1736, 2012) which allows for regularity in the parent process. This motivates the use of a realization of the GNS process as sampling design points. This method translates the high-dimensional optimization problem of selecting sampling sites into a low-dimensional optimization problem of searching for the optimal parameter sets in the GNS process. Simulation studies indicate that the proposed sampling design algorithm is more computationally efficient than traditional methods while achieving similar minimization of the criterion functions. While the traditional methods become computationally infeasible for sample size larger than a hundred, the proposed algorithm is applicable to a size as large as $$n=1024$$ . A real data example of finding the optimal spatial design for predicting sea surface temperature in the Pacific Ocean is also considered.

Modern neuroimaging technologies have substantially advanced the measurement of brain activity. Electroencephalogram (EEG) as a noninvasive neuroimaging technique measures changes in electrical voltage on the scalp induced by brain cortical activity. With its high temporal resolution, EEG has emerged as an increasingly useful tool to study brain connectivity. Challenges with modeling EEG signals of complex brain activity include interactions among unknown sources, low signal-to-noise ratio, and substantial between-subject heterogeneity. In this work, we propose a state space model that jointly analyzes multichannel EEG signals and learns dynamics of different sources corresponding to brain cortical activity. Our model borrows strength from spatially correlated measurements and uses low-dimensional latent states to explain all observed channels. The model can account for patient heterogeneity and quantify the effect of a subject's covariates on the latent space. The EM algorithm, Kalman filtering, and bootstrap resampling are used to fit the state space model and provide comparisons between patient diagnostic groups. We apply the developed approach to a case-control study of alcoholism and reveal significant attenuation of brain activity in response to visual stimuli in alcoholic subjects compared to healthy controls.

Program mutation is the process of generating syntactic variations of a base program and analyzing them by comparison with the base; this process is meaningful only to the extent that the mutants are semantically distinct from the base program, but that is not always the case. Two programs may be syntactically distinct yet semantically equivalent. The problem of identifying and weeding out equivalent mutants has eluded researchers for a long time. In this chapter we argue that researchers ought to abandon the overly ambitious goal of determining whether a program and its mutant are equivalent, and focus instead on the more modest, but sufficient, goal of estimating the number of equivalent mutants that a program is prone to generate.

Background Trovafloxacin is a broad-spectrum antibiotic, recently identified as an inhibitor of pannexin-1 (Panx1) channels. Panx1 channels are important conduits for the adenosine triphosphate (ATP) release from live and dying cells that enhances the inflammatory response of immune cells. Elevated extracellular levels ATP released upon injury activate purinergic pathways in inflammatory cells that promote migration, proliferation, phagocytosis, and apoptotic signals. Here, we tested whether trovafloxacin administration attenuates the neuroinflammatory response and improves outcomes after brain trauma. Methods The murine controlled cortical impact (CCI) model was used to determine whether in vivo delivery of trovafloxacin has anti-inflammatory and neuroprotective actions after brain trauma. Locomotor deficit was assessed using the rotarod test. Levels of tissue damage markers and inflammation were measured using western blot, qPCR, and immunofluorescence. In vitro assays were used to evaluate whether trovafloxacin blocks ATP release and cell migration in a chemotactic-stimulated microglia cell line. Results Trovafloxacin treatment of CCI-injured mice significantly reduced tissue damage markers and improved locomotor deficits. In addition, trovafloxacin treatment significantly reduced mRNA levels of several pro-inflammatory cytokines (IL-1β, IL-6, and TNF-α), which correlates with an overall reduction in the accumulation of inflammatory cell types (neutrophils, microglia/macrophages, and astroglia) at the injury zone. To determine whether trovafloxacin exerted these effects by direct action on immune cells, we evaluated its effect on ATP release and cell migration using a chemotactic-stimulated microglial cell line. We found that trovafloxacin significantly inhibited both ATP release and migration of these cells. Conclusion Our results show that trovafloxacin administration has pronounced anti-inflammatory and neuroprotective effects following brain injury. These findings lay the foundation for future studies to directly test a role for Panx1 channels in pathological inflammation following brain trauma. Electronic supplementary material The online version of this article (10.1186/s12974-018-1069-9) contains supplementary material, which is available to authorized users.

Mutation testing is the art of generating syntactic versions (called mutants) of a base program, and is widely used in software testing, most notably the assessment of test suites. Mutants are useful only to the extent that they are semantically distinct from the base program, but some may well be semantically equivalent to the base program, despite being syntactically distinct. Much research has been devoted to identifying, and weeding out, equivalent mutants, but determining whether two programs are semantically equivalent is a non-trivial, tedious, error-prone task. Yet in practice it is not necessary to identify equivalent mutants individually; for most intents and purposes, it suffices to estimate their number. In this paper, we are interested to estimate, for a given number of mutants generated from a program, the ratio of those that are equivalent to the base program; we refer to this as the Ratio of Equivalent Mutants (REM, for short). We argue, on the basis of analytical grounds, that the REM of a program may be estimated from a static analysis of the program, and that it can be used to analyze many mutation related properties of a program. The purpose/ aspiration of this paper is to draw attention to this potentially cost-effective approach to a longstanding stubborn problem.

The use of Bisphenol A (BPA) has widely been replaced in consumer products by analogs BPB, BPE, BPF, BPS, and BPAF. Recent studies have linked these substitutes to similar adverse health outcomes as BPA, including disruption of endocrine pathways in animal and human studies. We designed a novel MS method, developed specifically for this study, to capture the most relevant BPA alternatives, BPB, BPE, BPF, BPS, BPAF and 4-NP in human blood and urine to quantify potential in utero exposures. To our knowledge, this is the first study to explore in utero exposure to these BPA analogs and the first U.S. study to test for BPA in maternal/fetal pairs. The method was run on 30 paired maternal urine and fetal cord blood samples from mothers undergoing elective Caesarean sections. 90% of mothers and 77% of babies tested positive for at least one BP analog. 83% of mothers tested positive for BPAF, 60% for BPS, 57% for BPB, 17% for BPF and 7% for BPA. 57% of babies tested positive for BPAF and 50% for BPF. BPA and BPB were detected in one cord blood sample each. BPS was not detected in cord blood. BPE was not detected in any fetal cord blood or maternal urine samples. These findings demonstrate the pervasiveness of some BP analogs in pregnant women and their babies at birth.

Equivalent mutants are a constant source of aggravation in mutation testing because they distort mutation-based analysis; but the identification of equivalent mutants is known to be undecidable, in addition to being (in practice) tedious and error-prone. We argue that for most applications it is not necessary to individually identify equivalent mutants; rather it suffices to know/ estimate their number. In this paper, we discuss the specification and design of an automated tool that estimates the number of equivalent mutants generated from a base program by analyzing the source code of the program as well as the mutant generation policy.

Equivalent mutants are a major nuisance in mutation testing because they introduce a significant amount of bias. But weeding them out is difficult because it requires a detailed analysis of the source code of the base program and the mutant. In this paper we argue that for most applications, it is not necessary to identify equivalent mutants individually; rather it suffices to estimate their number. Also, we explore how we can estimate their number by a cursory/automatable analysis of the base program and the mutant generation policy.

Fast food restaurants and liquor stores—vice stores—have been shown to be more prevalent in predominantly Black and low income U.S. neighborhoods, and are associated with a number of health risks and social ills. The purpose of this study was to investigate in the City of Chicago vice store density and spatial distribution as a function of racial, socioeconomic, and other population characteristics; to examine spatial clustering among these outlets; and to study how store turnover follows population change over a 13-year period. We used spatial point process analysis to fit linear and non-linear models for the intensity function of stores. Spatial clustering was estimated using the K function. We found heterogeneous associations between stores and population characteristics, with the most consistent finding being a positive association between percent Black and liquor store exposure. A high degree of spatial clustering was evident, and liquor stores were more likely to stay in business over time than fast food restaurants. However, when liquor stores closed, they were more likely to be replaced by non-vice businesses. Results suggest that vice stores are associated with lower positions in racial and socioeconomic hierarchies, and this patterning is often durable over time.

Background Mixed models are a useful tool for evaluating the association between an outcome variable and genetic variables from a family-based genetic study, taking into account the kinship coefficients. When there are ultrahigh dimensional genetic variables (ie, p ≫ n), it is challenging to fit any mixed effect model. Methods We propose a two-stage strategy, screening genetic variables in the first stage and then fitting the mixed effect model in the second stage to those variables that survive the screening. For the screening stage, we can use the sure independence screening (SIS) procedure, which fits the mixed effect model to one genetic variable at a time. Because the SIS procedure may fail to identify those marginally unimportant but jointly important genetic variables, we propose a joint screening (JS) procedure that screens all the genetic variables simultaneously. We evaluate the performance of the proposed JS procedure via a simulation study and an application to the GAW20 data. Results We perform the proposed JS procedure on the GAW20 representative simulated data set (n = 680 participant(s) and p = 463,995 CpG cytosine-phosphate-guanine [CpG] sites) and select the top d = ⌊n/ log(n)⌋ variables. Then we fit the mixed model using these top variables. Under significance level, 5%, 43 CpG sites are found to be significant. Some diagnostic analyses based on the residuals show the fitted mixed model is appropriate. Conclusions Although the GAW20 data set is ultrahigh dimensional and family-based having within group variances, we were successful in performing subset selection using a two-step strategy that is computationally simple and easy to understand.

Identifying homogeneous subgroups of variables can be challenging in high dimensional data analysis with highly correlated predictors. The generalized fused lasso has been proposed to simultaneously select correlated variables and identify them as predictive clusters (grouping property). In this article, we study properties of the generalized fused lasso. First, we present a geometric interpretation of the generalized fused lasso along with discussion of its persistency. Second, we analytically show its grouping property. Third, we give comprehensive simulation studies to compare our version of the generalized fused lasso with other existing methods and show that the proposed method outperforms other variable selection methods in terms of prediction error and parsimony. We describe two applications of our method in soil science and near infrared spectroscopy studies. These examples having vastly different data types demonstrate the flexibility of the methodology particularly for high-dimensional data.

The relatively low cost of lands along with a privileged location near an urban center attracted industry to the Meadowlands of New Jersey and the absence of regulations resulted in vast amounts of industrial waste emitted into the air and dumped to nearby estuaries and marshlands. Hurricane Sandy created an unprecedented sea surge that overtopped berms and tide gates and extensively flooded approximately 22.8 km2 of a low lying basin that includes Berry’s Creek, a tributary to the Hackensack River and well known for its legacy of high levels of contamination. The sea surge connected Berry’s Creek with eastern creeks that flow into the Hackensack River for several tidal cycles. The objectives of this study were to establish a baseline for organic pollutants and heavy metals post Superstorm Sandy, determine whether contaminants from highly contaminated areas moved to the eastern creeks during the surge and measure contaminant gradients around tide gates. Cadmium, mercury and chromium were the most abundant contaminants in sediments, and pollutants responsible for the highest ecological risk were Hg and polychlorinated biphenyls (PCBs). Concentrations of PCBs were higher in the western creeks and contrary to metals did not show concentration gradients from either side of tide gates. Massive export of contaminants from western to eastern creeks due to the surge was not apparent. The abundance of heavy metals in the vicinity of tide gates shows that they play a role in their distribution across the estuary.

The rise in reported prevalence rates of autism spectrum disorders (ASDs) is a national concern that continues to grow at a record pace. New Jersey has the highest prevalence rate of autism spectrum disorders (ASDs) among states surveyed, with approximately 1 in 45 children diagnosed. The pilot study focused on toxins potentially linked to autism: arsenic, lead, manganese, mercury, organophosphate pesticides, polychlorinated biphenyls, trichloroethylene, and vinyl chloride. In northern NJ there were approximately 4600 Known Contaminated Sites (KCSNJ) where these toxins were detected. A total of 269,790 sample detections were identified. Our objective was to identify and map these sites, and identify methods by which more robust contaminant data could be collected and analyzed. This study resulted in eight original maps showing sample detections. These maps will aid researchers and public health advocates in future analyses exploring links between autism and these toxins. Concentrations of multiple toxins associated with ASDs were most dense near urban industrial or mixed residential/industrial areas, though no conclusions can be made regarding association or causality between the sample detections and autism. Based in part on this study, NJDEP has made and will continue to make improvements to contaminant data collection systems.