Sources Of Variation In Data Research Articles

Accumulation of the Toxic Metal Mercury in Multiple Tissues of Marine-Associated Birds from South Florida.

One of the best studied global "hot spots" for ecological mercury (Hg) contamination is south Florida (USA), where elevated Hg concentrations in environmental media and regional wildlife were first described over thirty years ago. While Hg contamination has lessened in this region, it is still critical to monitor Hg uptake and potential risks in south Florida wildlife, especially in marine-associated birds, which are known to accumulate potentially toxic Hg levels. In this study, total Hg (THg) concentrations were measured in liver, kidney, muscle, and feathers of 101 individuals from seven species of south Florida birds: brown pelican Pelecanus occidentalis, double-crested cormorant Phalacrocorax auratus, herring gull Larus argentatus, laughing gull Leucophaeus atricilla, northern gannet Morus bassanus, royal tern Thalasseus maximus, and osprey Pandion halietus. A sizeable proportion of individuals (> 40%) were found to contain THg concentrations in internal tissues that exceeded estimated toxicity thresholds for Hg-related effects. Certain species, especially osprey, were found to exhibit a higher rate of threshold exceedances than others and should continue to be monitored for Hg-related effects in future studies. Feather THg concentrations exhibited a lower rate of toxicity threshold exceedances (12%) and were not significantly correlated with those in internal tissues in most cases, suggesting that they may not be well suited for monitoring Hg exposure in these species unless sources of data variation can be better understood. The results of the present study contribute significantly to our understanding of trends in Hg accumulation and Hg-related health risks in south Florida marine-associated birds.

English

Because of, well established relationship between seasonal variability and diseases dynamism we embarked here in evaluating recurrently diagnosed diseases dynamism at Korhogo General Hospital in Northern Côte d’Ivoire from 2014 to 2018. For this purpose, clinical data with regard 1707 patients were collected and clusterized in 25 diseases cases. Data have been submitted to multivariate and computational statistical survey with the purpose to assess recurrently diagnosed diseases dynamism from 2014 to 2018. Results supported strong effect of year’s dynamism on recurrent diseases variability by exhibiting high frequency of malaria and hypertension diseases cases. Findings also revealed two diseases clustering groups in terms of diseases variability dynamism. Of note, malaria and high blood pressure diseases exhibited a contrasting attitude in assessing recurrently diagnosed diseases dynamism. Indeed, high blood pressure disease exhibited regular increasing dynamism by contrast to malaria that displayed a relative irregular increasing dynamism. Variance homogeneity tests and descriptive clustering analysis, clusterized recurrently diagnosed diseases at Korhogo General Hospital in two distinct groups, associated to malaria and hypertension, in terms of those diseases increasing dynamism. Diseases discriminated as exhibiting regular increasing dynamism (i.e. diabetes, gastritis, asthma, gastroenteritis and bronchitis) and associated to hypertension, meanly claim to be influenced by patients age parameter as opposed to those showing irregular increasing dynamism; i.e., malaria and influenza (p>0.05). Furthermore, findings revealed cardiac pathologies dynamism as relatively influenced by patients gender and age as opposed to lumbosciatic, back pain, pneumonia  and osteoarthritis diseases dynamism that exhibited sole age parameter as a source of data variability (p=0.02-0.07). To conclude our study highlighted a relative yearly increasing diseases variability and revealed two tendencies in assessing recurrently diagnosed diseases dynamism at Korhogo General Hospital from 2014 to 2018. Key words: Recurrently diagnosed diseases dynamism, Bartlett, Fligner-Killeen and Tukey statistical tests, Korhogo General Hospital.

Determination of ethyl glucuronide (EtG) in blood samples using partial least squares discriminant analysis applied to surface-enhanced Raman spectroscopy

Consumption of alcohol and problems related to alcohol vary widely around the world. Especially illegally produced and distributed alcohols have a great risk for human health, since they include high quantity of toxic substances. Ethanol measurements have high specificity for excessive alcohol intake. Ethyl Glucuronide (EtG) is considered as a direct biomarker of recent ethanol consumption.The study aims to identify EtG in blood samples by using Raman Spectroscopy. Silver colloidal nanoparticles were synthesized to obtain SERS (Surface-Enhanced Raman Spectroscopy) spectra of blood samples and EtG. PLS-DA (Partial Least Squares Discriminant Analysis) models were built on the collected SERS spectra. It is observed that EtG and the blood samples taken from people using alcohol are in the same group and the blood samples taken from no alcohol users are in a separate cluster from EtG. The sources of data variability are modelled by the so-called Latent Variables (LVs). The percentage of LVs were found to be 29.53% and 8.34%, respectively.In the study, it has been observed that the level of EtG changes according to the level of ethanol in blood samples. However, there is no study on the detection of EtG in blood with Raman spectroscopy. Outcomes of the present study encourage the feasibility of the application of Raman Spectroscopy for determination of EtG in blood samples.

TSEE: an elastic embedding method to visualize the dynamic gene expression patterns of time series single-cell RNA sequencing data

BackgroundTime series single-cell RNA sequencing (scRNA-seq) data are emerging. However, the analysis of time series scRNA-seq data could be compromised by 1) distortion created by assorted sources of data collection and generation across time samples and 2) inheritance of cell-to-cell variations by stochastic dynamic patterns of gene expression. This calls for the development of an algorithm able to visualize time series scRNA-seq data in order to reveal latent structures and uncover dynamic transition processes.ResultsIn this study, we propose an algorithm, termed time series elastic embedding (TSEE), by incorporating experimental temporal information into the elastic embedding (EE) method, in order to visualize time series scRNA-seq data. TSEE extends the EE algorithm by penalizing the proximal placement of latent points that correspond to data points otherwise separated by experimental time intervals. TSEE is herein used to visualize time series scRNA-seq datasets of embryonic developmental processed in human and zebrafish. We demonstrate that TSEE outperforms existing methods (e.g. PCA, tSNE and EE) in preserving local and global structures as well as enhancing the temporal resolution of samples. Meanwhile, TSEE reveals the dynamic oscillation patterns of gene expression waves during zebrafish embryogenesis.ConclusionsTSEE can efficiently visualize time series scRNA-seq data by diluting the distortions of assorted sources of data variation across time stages and achieve the temporal resolution enhancement by preserving temporal order and structure. TSEE uncovers the subtle dynamic structures of gene expression patterns, facilitating further downstream dynamic modeling and analysis of gene expression processes. The computational framework of TSEE is generalizable by allowing the incorporation of other sources of information.

Aesthetic compatibility assessment of consolidants for wall paintings by means of multivariate analysis of colorimetric data

Background and methodsWall paintings and architectural surfaces in outdoor environments are exposed to several physical, chemical and biological agents, hence they are often treated with different products to prevent or slow down their deterioration. Among the factors that have to be taken into account in the selection of the most suitable treatment for decorated surfaces, the aesthetic compatibility with the substrate is of great importance in the cultural heritage field; minimizing colour variation after treatment application is a crucial issue in particular for painted surfaces. In the framework of the European Project Nanomatch the color variation induced on wall painting mock-ups by the two innovative consolidants (calcium alkoxides) developed was evaluated using colorimetry in comparison with two traditional products. In this work these innovative consolidants have been also tested in combination with two commercial biocides and the results of colorimetric measurements discussed. Moreover, as the univariate approach didn’t allow to draw clear conclusions on the relation between the different sources of data variability, multivariate analysis was performed on colorimetric data.ResultsPrincipal Component Analysis and multi-way Parallel Factor Analysis (PARAFAC) were successfully applied to colorimetric data to investigate the short-term effects of the application of different consolidants on wall painting surfaces, making it possible to study at the same time the different sources of data variability, i.e. treatments, painting techniques, pigments. Finally, a ranking list of the treatments under study in terms of colour variation induced on the surface was established, in function of the painting technique and pigment, taking also in consideration the combination consolidant/biocide. In particular, given the true multi-way nature of the data, PARAFAC model turned out to be extremely useful in the study of the dependence of colour variation on pigments, a critical issue for painted surfaces, that was not clear using univariate approach.ConclusionsMultivariate approach to colorimetric data and especially 3-way PARAFAC method resulted a powerful technique to evaluate in short-term the color compatibility of consolidants for wall paintings, improving data interpretation and visualization, and thus outperforming the univariate statistical analysis.

Tensorial blind source separation for improved analysis of multi-omic data

There is an increased need for integrative analyses of multi-omic data. We present and benchmark a novel tensorial independent component analysis (tICA) algorithm against current state-of-the-art methods. We find that tICA outperforms competing methods in identifying biological sources of data variation at a reduced computational cost. On epigenetic data, tICA can identify methylation quantitative trait loci at high sensitivity. In the cancer context, tICA identifies gene modules whose expression variation across tumours is driven by copy-number or DNA methylation changes, but whose deregulation relative to normal tissue is independent of such alterations, a result we validate by direct analysis of individual data types.

Learning by coincidence: Siamese networks and common variable learning

We consider the statistical problem of learning a common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach is useful in particular in exploratory, data-driven applications, where neither a model nor label information is available. In recent years, many researchers have successfully applied Siamese neural networks to obtain an embedding of data which corresponds to a “semantic similarity”. We present an interpretation of this “semantic similarity” as learning of equivalence classes. We demonstrate the ability of Siamese networks to learn common variability in a range of experiments on synthetic and real-world data, and demonstrate the potential of Siamese networks to provide new leads for data-driven research through unsupervised learning in cancer data.

Sella turcica dimensions between 7 and 13 years: a novel radiographic method for age estimation

Age estimation of the living is becoming a relevant field of application of foren- sic anthropology, where the development of novel methods is urging (1). Several articles highlight the relation with age of different metrical parameters of the sella turcica (2,3), although no study so far has produced regression formulae which may be applicable to the forensic context. The aim of this study was to evaluate the metrical standards of three different measurements of sella turcica (length, depth, diameter) in 177 lateral cephalometric radiograms belonging to male and female individuals aged between 7 and 13 years in order to find standards useful for age estimation. Results were evaluated by two-way ANOVA. Sella diameter was significantly larger in older children (p<0.01), while sella depth was larger in males than in females (p<0.01); there was no significant gender x age interaction in any variable. Principal component analysis (PCA) was conducted to highlight the sources of variability in data. The first principal component accounted for 76% of the overall variance and it was closely correlated with length and diameter (r=0.93 and r=0.92, respectively, p<0.01). The linear regression model fitted on age and diameter measures yielded the following equation: age (years)=3.81*diameter (cm)+6.12. Slope and intercept 95% CI were respectively 4.64 to 7.61 years/cm and 2.34 to 5.28 years. The related coefficient of determination was R2=0.123, while the root mean square error was 1.74 years. The present results provide a novel method useful for age estimation in the living minors: further studies are needed in order to test its applicability to the forensic scenario.

The identification of causal effects in environmental and energy economics

Environmental and energy economics has grown broad and diverse. The challenges of managing environmental quality, specially in light of climate change and growing energy demands, are well-recognized and becoming increasingly important. t the same time, the research methods of environmental and energy economics continue to advance and provide a basis for ore informed decision making. Mirroring trends in empirical economics generally, environmental and energy economists re placing ever more emphasis on careful identification strategies that underlie conclusions about causal effects. Environmental and energy economists are making greater use of randomized laboratory and field experiments, have rained their eyes to spot natural experiments, and are refining quasi-experimental methods for use in observational studies. he emphasis on identification and causality has brought with it more careful thinking about the sources of variation in data, he presence of self-selection, the assumptions needed for consistent and/or unbiased estimation, and the importance of stablishing the robustness of estimates across possible specifications. With increased data collection capabilities and efforts n the part of government agencies, nonprofit organizations and businesses to increase data availability, these identification ools, in turn, provide important synergistic opportunities. This special issue of the Journal of Economic Behavior & Organization (JEBO) on “The Identification of Causal Effects in nvironmental and Energy Economics” showcases some of the leading research in the field. The included articles were art of a workshop in July 2013 generously hosted by the Howard H. Baker Jr. Center for Public Policy at the University of ennessee. The Baker Center was established to honor the legacy of Senator Baker, whose contributions to public policy ere numerous and include facilitating passage of the Clean Water Act of 1972 and the Clean Air Act of 1970. As the Baker enter has developed its portfolio of research and policy engagement, it has maintained a steady course in focusing on nvironmental and energy policy issues. Consistent with this agenda, the workshop attracted papers that span a wide range f methodologies and policy-relevant topics within the field of environmental and energy economics. We thank Matthew urray, the Director of the Baker Center, along with the Baker Center staff, for their help in making the workshop such a uccess. Many of the papers focus on topics related to demand for electricity, and three of them exploit high resolution residential illing data. Benjamin Gilbert and Joshua Graff Zivin investigate how exposure to expenditure information via the receipt f an electricity bill affects the pattern of electricity consumption. Their identification strategy relies on exogenous variaion in billing cycles and the availability of hourly consumption data from smart meters. They find reduced consumption ollowing receipt of an electricity bill, with the implication that spending “reminders” can reduce peak demand, particuarly during summer months. Katrina Jessoe, David Rapson, and Jeremy Smith consider how shifting to time-of-use billing ffects electricity demand using a regression discontinuity approach. They find a surprising response where the program ffectively lowered the price of electricity: they observe a decrease rather than an increase in consumption, for which hey conjecture explanations based on dynamic considerations and behavioral factors. The paper by Matthew Harding and lice Hsiaw focuses entirely on psychological and behavioral motives related to voluntary energy conservation. Based on

Efficient distributed monitoring with active Collaborative Prediction

Isolating users from the inevitable faults in large distributed systems is critical to Quality of Experience. We formulate the problem of probe selection for fault prediction based on end-to-end probing as a Collaborative Prediction (CP) problem. On an extensive experimental dataset from the EGI (European Grid Initiative) grid, the combination of the Maximum Margin Matrix Factorization approach to CP and Active Learning shows excellent performance, reducing the number of probes typically by 80% to 90%. Comparison with other Collaborative Prediction strategies show that Active Probing is most efficient at dealing with the various sources of data variability.

Normalization of miRNA qPCR high-throughput data: a comparison of methods

Low-density quantitative real-time PCR (qPCR) arrays are often used to profile expression patterns of microRNAs in various biological milieus. To achieve accurate analysis of expression of miRNAs, non-biological sources of variation in data should be removed through precise normalization of data. We have systematically compared the performance of 19 normalization methods on different subsets of a real miRNA qPCR dataset that covers 40 human tissues. After robustly modeling the mean squared error (MSE) in normalized data, we demonstrate lower variability between replicates is achieved using various methods not applied to high-throughput miRNA qPCR data yet. Normalization methods that use splines or wavelets smoothing to estimate and remove Cq dependent non-linearity between pairs of samples best reduced the MSE of differences in Cq values of replicate samples. These methods also retained between-group variability in different subsets of the dataset.

Correlation of Alzheimer disease neuropathologic changes with cognitive status: a review of the literature.

Clinicopathologic correlation studies are critically important for the field of Alzheimer disease (AD) research. Studies on human subjects with autopsy confirmation entail numerous potential biases that affect both their general applicability and the validity of the correlations. Many sources of data variability can weaken the apparent correlation between cognitive status and AD neuropathologic changes. Indeed, most persons in advanced old age have significant non-AD brain lesions that may alter cognition independently of AD. Worldwide research efforts have evaluated thousands of human subjects to assess the causes of cognitive impairment in the elderly, and these studies have been interpreted in different ways. We review the literature focusing on the correlation of AD neuropathologic changes (i.e. β-amyloid plaques and neurofibrillary tangles) with cognitive impairment. We discuss the various patterns of brain changes that have been observed in elderly individuals to provide a perspective for understanding AD clinicopathologic correlation and conclude that evidence from many independent research centers strongly supports the existence of a specific disease, as defined by the presence of Aβ plaques and neurofibrillary tangles. Although Aβ plaques may play a key role in AD pathogenesis, the severity of cognitive impairment correlates best with the burden of neocortical neurofibrillary tangles.

Application of latent growth and growth mixture modeling to identify and characterize differential responders to treatment for COPD

ObjectiveTo explore the utility of applying growth mixture models (GMMs) in secondary analyses of clinical trials to identify sources of variability in data reported by patients with COPD. MethodsAnalyses were performed on data from two 6-month clinical trials comparing indacaterol and open-label tiotropium or blinded salmeterol and the first six months of a 12-month trial comparing indacaterol and blinded formoterol. Latent growth model (LGM) analyses were conducted to explore the response of the SGRQ Symptoms score from baseline to six months and GMM analyses were evaluated as a method to identify latent classes of differential responders. ResultsVariability in SGRQ Symptom scores was found suggesting subsets of patients with differential response to treatment. GMM analyses found subsets of non-responders in all trials. When the responders were analyzed separately from non-responders, there were increased treatment effects (e.g., symptoms score improvement over six months for whole groups: indacaterol=8–12 units, tiotropium=7 units, salmeterol=9 units, formoterol=11 units. Responder subgroup improvement: indacaterol=9–21 units, tiotropium=7 units, salmeterol=10 units, formoterol=20 units). Responders had significantly different baseline SGRQ Symptom scores, smoking history, age, and mMRC dyspnea scores than non-responders. ConclusionsPatients with COPD represent a heterogeneous population in terms of their reporting of symptoms and response to treatment. GMM analyses are able to identify sub-groups of responders and non-responders. Application of this methodology could be of value on other endpoints in COPD and in other disease areas.

EVALUATING CONSUMER ACCEPTANCE TESTS BY THREE-WAY INTERNAL PREFERENCE MAPPING OBTAINED BY PARALLEL FACTOR ANALYSIS (PARAFAC)

ABSTRACT In this work, it is demonstrated that consumer acceptance analysis can be evaluated by simultaneously considering several attributes using a three-way internal preference map obtained by parallel factor analysis (PARAFAC). Considerations regarding the building of this three-way map by PARAFAC are reported. Pilot case studies with real data sets from herb cakes and beef burgers are also carried out, and comparisons with results from regular internal preference maps are obtained by principal component analysis. Three-way internal preference maps enable the simultaneous analysis of interactions among consumer preferences, products and different evaluated attributes, which facilitate the selection of favorite samples. This method highlights the efficiency of the three-way analysis of consumer acceptance data with different sources of data variability, allowing the extraction of relevant information and the graphic display of this information with improved interpretability. Three-way internal preference mapping is a useful tool for the analysis of consumer acceptance tests, which can provide a more evidence-based and general interpretation of data. PRACTICAL APPLICATIONS Three-way internal preference mapping is another useful tool for the analysis of consumer acceptance tests, allowing the extraction of more relevant information and the graphic display of this information with improved interpretability. This tool makes it possible to simultaneously analyze the interactions among consumer preferences, products and different evaluated attributes, which can facilitate the selection of favorite samples. Furthermore, it enables a comparison of the overall performance of the samples in consumer acceptance tests, simultaneously taking into account the influence of all analyzed attributes. This method is useful in new product development and product improvement studies in research institutions and industries.

Likelihood ratio model for classification of forensic evidence

One of the problems of analysis of forensic evidence such as glass fragments, is the determination of their use-type category, e.g. does a glass fragment originate from an unknown window or container? Very small glass fragments arise during various accidents and criminal offences, and could be carried on the clothes, shoes and hair of participants. It is therefore necessary to obtain information on their physicochemical composition in order to solve the classification problem. Scanning Electron Microscopy coupled with an Energy Dispersive X-ray Spectrometer and the Glass Refractive Index Measurement method are routinely used in many forensic institutes for the investigation of glass. A natural form of glass evidence evaluation for forensic purposes is the likelihood ratio— LR = p( E|H 1)/ p( E|H 2). The main aim of this paper was to study the performance of LR models for glass object classification which considered one or two sources of data variability, i.e. between-glass-object variability and(or) within-glass-object variability. Within the proposed model a multivariate kernel density approach was adopted for modelling the between-object distribution and a multivariate normal distribution was adopted for modelling within-object distributions. Moreover, a graphical method of estimating the dependence structure was employed to reduce the highly multivariate problem to several lower-dimensional problems. The performed analysis showed that the best likelihood model was the one which allows to include information about between and within-object variability, and with variables derived from elemental compositions measured by SEM-EDX, and refractive values determined before (RI b) and after (RI a) the annealing process, in the form of dRI = log 10|RI a − RI b|. This model gave better results than the model with only between-object variability considered. In addition, when dRI and variables derived from elemental compositions were used, this model outperformed two other classification methods in classifying test set observations into car or building windows.

Extraneous variables and their influence on reflectance-based measurements of leaf water content

Leaf water indices based on leaf reflectance may depend not only on the variable of interest, leaf water content, but may also be influenced by a variety of extraneous variables, leading to considerable data variability if such extraneous variables are not eliminated or taken into account. Here, we examined the nature of three potential extraneous variables: homogeneity of the leaf target area, the distance between a primary reflecting leaf and background material, and measurement sensitivity at various wavelengths. Although leaf water indices appear to be homogeneously distributed between major leaf veins, they may fluctuate substantially in areas where major veins are present. Leaf water indices may also depend to some extent on the distance between a primary reflecting leaf and any reflecting background material, at least for small distances. Leaf water indices utilizing the 970 or 1200 nm water absorption bands have been shown to be rather insensitive to changes in leaf water content, potentially resulting in low signal-to-noise ratios, an additional source of data variability.

Regression analysis and modelling of data acquisition for SELDI-TOF mass spectrometry

Pre-processing of SELDI-TOF mass spectrometry data is currently performed on a largel y ad hoc basis. This makes comparison of results from independent analyses troublesome and does not provide a framework for distinguishing different sources of variation in data. In this article, we consider the task of pooling a large number of single-shot spectra, a task commonly performed automatically by the instrument software. By viewing the underlying statistical problem as one of heteroscedastic linear regression, we provide a framework for introducing robust methods and for dealing with missing data resulting from a limited span of recordable intensity values provided by the instrument. Our framework provides an interpretation of currently used methods as a maximum-likelihood estimator and allows theoretical derivation of its variance. We observe that this variance depends crucially on the total number of ionic species, which can vary considerably between different pooled spectra. This variation in variance can potentially invalidate the results from naive methods of discrimination/classification and we outline appropriate data transformations. Introducing methods from robust statistics did not improve the standard errors of the pooled samples. Imputing missing values however-using the EM algorithm-had a notable effect on the result; for our data, the pooled height of peaks which were frequently truncated increased by up to 30%.

THE CONCEPT OF DISTRIBUTION

This paper is a personal exploration of where the ideas of “distribution” that we are trying to develop in students come from and are leading to, how they fit together, and where they are important and why. We need to have such considerations in the back of our minds when designing learning experiences. The notion of “distribution” as a lens through which statisticians look at the variation in data is developed. I explore the sources of variation in data, empirical versus theoretical distributions, the nature of statistical models, sampling distributions, the conditional nature of distributions used for modelling, and the underpinnings of inference. First published November 2006 at Statistics Education Research Journal Archives

Analysis of sensory data of Aceto Balsamico Tradizionale di Modena (ABTM) of different ageing by application of PARAFAC models

Aceto Balsamico Tradizionale di Modena is a typical Italian food product of protected denomination of origin, obtained by alcoholic fermentation and acetic bio-oxidation of cooked musts, and it is aged for at least 12 years in series of wooden casks. The product suitable for marketing is qualified by sensory examination on the whole of 13 sensory parameters. In this study, a series of six casks for each of seven different producers have been investigated by an expert Panel of eight judges, aiming at (i) assessing the degree of variability of the different sensorial attributes with samples ageing, and (ii) evaluating the similarity/dissimilarity among the various parameters together with the degree of agreement of the panellists. Given the three-way nature of the data (samples × panellists × sensory attributes) the PARAFAC method has been used, and a satisfactory model was obtained, highlighting the efficacy of three-way analysis in dealing with the different sources of data variability, extracting the relevant information and displaying it in a simple and interpretable manner.

Data Variability in Rheological Measurement of Semi-Solid Foods: Effects of Loading Normal Force

AbstractPrevious studies involving rheological measurement of semi-solid foods have reported a large amount of data variability, but have focused little on understanding the cause of such variability. This project examined whether differences in normal force have an effect on the variability of rheological measurements. Experimental methods focused on error introduced during sample loading; specifically whether normal force application during loading influenced the storage (G’) and loss (G”) moduli of semi-solid and liquid foods. Samples were loaded to 5 or 20 N between the parallel plates of a TA-1000N rheometer and tested immediately. For all semi-solid products tested, normal force application during sample loading did significantly affect oscillatory parameters, with G’ and G” measurements increasing up to 50 % with greater normal force. However, loading normal force did not significantly influence the parameters measured for the liquid sample. This suggests that differences in normal force during loading could be a significant source of data variability during rheological measurement of semi-solid products.