Search

Individuals and communities increasingly depend on, and fill their lives with, machine cultures, in the form of both interfaces and infrastructures. This global push for machine cultures has given rise to an increasing demand for data and engendered a proliferation of public, private and public-private dataset repositories. While datasets form a foundational element of machine cultures, they rarely come into focus as objects of critical study. But in recent years a critical discursive formation on datasets has begun to emerge, which disturbs the idea of datasets as operational instruments of digital knowledge production and seek to instead ‘bring people back in’. The present article identifies these preliminary explorations as ‘critical dataset studies’ and draws on critical archival studies to articulate the ethico-political surfaced by these studies. Specifically it argues that critical dataset studies shows the need for an expanded ethical and conceptual approach to datasets that not only relies on linear notions of deletion and accountability but also on iterative frameworks of remains and response-ability.

In this article, we describe qregsel, a community-contributed command that implements a copula-based sample-selection correction for quantile regression recently proposed by Arellano and Bonhomme (2017, Econometrica 85: 1–28). The command allows the user to model selection in quantile regressions by using either a Gaussian or a one-dimensional Frank copula. We illustrate the use of qregsel with two examples. First, we apply the method to the fictional dataset used in the Stata Base Reference Manual for the heckman command. Second, we replicate part of the empirical application of the original article using data for the United Kingdom that cover the period 1978–2000 to compare wages of males and females at different quantiles.

We develop purely nonparametric methods for the analysis of repeated measures designs with missing values. Hypotheses are formulated in terms of purely nonparametric treatment effects. In particular, data can have different shapes even under the null hypothesis and therefore, a solution to the nonparametric Behrens-Fisher problem in repeated measures designs will be presented. Moreover, global testing and multiple contrast test procedures as well as simultaneous confidence intervals for the treatment effects of interest will be developed. All methods can be applied for the analysis of metric, discrete, ordinal, and even binary data in a unified way. Extensive simulation studies indicate a satisfactory control of the nominal type-I error rate, even for small sample sizes and a high amount of missing data (up to 30%). We apply the newly developed methodology to a real data set, demonstrating its application and interpretation.

A comprehensive analysis of the motivations, gap acceptance, duration, and speed adjustment of heavy vehicle lane changes (LC) is conducted in this paper. An rich data set containing 433 discretionary LC trajectories of heavy vehicles is used in this study and the data set is divided into two data sets based on the LC direction (LC to the left lane [LCLL] and LC to the right lane [LCRL]) for comparison. It is seen that LCLL and LCRL have significantly different motivations, which also results in different gap acceptance behavior. However, the LC direction does not significantly influence the LC duration. The navigation speed significantly influences the LC duration of heavy vehicles and the LC duration will decrease with the increase of speed, indicating the substantial impact of traffic conditions on LC duration. An obvious speed synchronization phenomenon is found in the process of LCLL, which is not the case in LCRL. The results of this study highlight the distinct characteristics of the LC of heavy vehicles and produce a better understanding of the lane-changing behaviors of heavy vehicles. The fitted distributions of LC duration and further investigation into gap acceptance behaviors may be used for microscopic traffic simulation and auto driving.

We employ a symbolic transfer entropy panel data test in a large-scale data set to provide new insights on the worldwide short-term causality relations between growth and inbound tourists. Using a large data set on 145 countries from the World Bank Open Data website, we show that, despite the evidently strong correlation between these two magnitudes, claiming that the increases in inbound tourists Granger-cause positive shocks in GDP is not supported by the data. By contrast, the data seem to point out in the direction of a reverse causality in that it is GDP growth what drives international inbound tourists in the short run. JEL classification C12, C14, C33, C55.

This paper addresses the issue of detecting dominating failure modes of a system from a two-dimensional warranty data set by analyzing conditional failure profile of the system. Two testing procedures have been proposed to test whether any of the failure modes is dominating at a particular time interval and whether there is a change of the failure profile from one time interval to another disjoint time interval, conditioning on a given usage layer. Detecting the problematic failure modes early from the conditional failure profile and taking appropriate actions to reduce the conditional failure probability of the system can significantly reduce both tangible and intangible costs of poor reliability in any manufacturing industry. On the other hand, the study of possible changes of conditional failure profiles has a significant role to assess the field performance of items from one time interval to another time interval for a particular choice of usage layer. The utility of this study is explored with the help of a real-life data set.

Using in-store ambulatory eye-tracking, the authors investigate the extent to which lateral and vertical biases drive consumers’ attention in a grocery store environment. The data set offers a complete picture of both where the shopper is located and the shopper’s field of view and visual fixations during the trip. The authors address two research questions: First, do shoppers have a higher propensity to pay attention to products on their left or right side as they traverse an aisle (i.e., is the right side the “right” side)? Second, do shoppers tend to pay more attention to products at their eye level (i.e., is eye level “buy level”)? The authors utilize the exogenous variations in the direction by which shoppers traverse an aisle to identify lateral bias. The exogenous variation of shoppers’ eye-level positions is used to identify vertical bias. The authors find that shoppers pay more attention to products on their right side when traversing an aisle. Contrary to many practitioners’ belief, eye level is not “buy level”; rather, the product level that has the greatest propensity to capture shoppers’ attention is approximately 14.7 inches below eye level (which is around chest level).

In the United States, fatalities from vehicle–bicycle crashes have been increasing since 2010. A total of 857 cyclists were struck and killed in 2018 which is an increase from 623 fatalities in 2010. One promising countermeasure is Automatic Emergency Braking (AEB), which can help prevent and/or mitigate many vehicle–bicycle crashes. AEB is a vehicle-based system that can detect and mitigate an impending crash. The goal of this study was to elucidate U.S. vehicle–bicycle crashes and examine related factors to estimate AEB effectiveness. This study used a unique in-depth vehicle–bicycle crash study dataset collected under the collaboration of the Washtenaw Area Transportation Study (WATS) and the Toyota Collaborative Research Center conducted in southeast Michigan from 2011 to 2013. The WATS database provides in-depth investigations of vehicle–bicycle crashes in the United States. The characteristics of the WATS vehicle–bicycle crashes were validated against the Fatality Analysis Reporting System and the General Estimate System. The WATS database cases were examined to estimate the potential effectiveness of AEB to prevent or mitigate vehicle–bicycle collisions. In 60% of the WATS cases, cyclists were in the road for more than 1 s before impact. Assuming that a hypothetical AEB system requires a minimum of 1 s for detection and brake activation, these collisions would potentially be avoided or mitigated. However, for the remaining cases with less than 1 s of time to react (40% of cases), that AEB system would be challenged to avoid or mitigate the collision.

Current research has evolved in such a way scientists must not only adequately describe the algorithms they introduce and the results of their application, but also ensure the possibility of reproducing the results and comparing them with those obtained through other approximations. In this context, public data sets (sometimes shared through repositories) are one of the most important elements for the development of experimental protocols and test benches. This study has analysed a significant number of CS/ML ( Computer Science/ Machine Learning) research data repositories and data sets and detected some limitations that hamper their utility. Particularly, we identify and discuss the following demanding functionalities for repositories: (1) building customised data sets for specific research tasks, (2) facilitating the comparison of different techniques using dissimilar pre-processing methods, (3) ensuring the availability of software applications to reproduce the pre-processing steps without using the repository functionalities and (4) providing protection mechanisms for licencing issues and user rights. To show the introduced functionality, we created STRep (Spam Text Repository) web application which implements our recommendations adapted to the field of spam text repositories. In addition, we launched an instance of STRep in the URL https://rdata.4spam.group to facilitate understanding of this study.

Although multiple organizational-level databases are frequently combined into one data set, there is no overview of the matching methods (MMs) that are utilized because the vast majority of studies does not report how this was done. Furthermore, it is unclear what the differences are between the utilized methods, and it is unclear whether research findings might be influenced by the utilized method. This article describes four commonly used methods for matching databases and potential issues. An empirical comparison of those methods used to combine regularly used organizational-level databases reveals large differences in the number of observations obtained. Furthermore, empirical analyses of these different methods reveal that several of them produce both systematic and random errors. These errors can result in erroneous estimations of regression coefficients in terms of direction and/or size as well as an issue where truly significant relationships might be found to be insignificant. This shows that research findings can be influenced by the MM used, which would argue in favor of the establishment of a preferred method as well as more transparency on the utilized method in future studies. This article provides insight into the matching process and methods, suggests a preferred method, and should aid researchers, reviewers, and editors with both combining multiple databases and describing and assessing them.

Background: The Oxford Big Data Institute, multiple sclerosis (MS) physicians and Novartis aim to address unresolved questions in MS with a novel comprehensive clinical trial data set. Objective: The objective of this study is to describe the Novartis–Oxford MS (NO.MS) data set and to explore the relationships between age, disease activity and disease worsening across MS phenotypes. Methods: We report key characteristics of NO.MS. We modelled MS lesion formation, relapse frequency, brain volume change and disability worsening cross-sectionally, as a function of patients’ baseline age, using phase III study data (≈8000 patients). Results: NO.MS contains data of ≈35,000 patients (>200,000 brain images from ≈10,000 patients), with >10 years follow-up. (1) Focal disease activity is highest in paediatric patients and decreases with age, (2) brain volume loss is similar across age and phenotypes and (3) the youngest patients have the lowest likelihood (Conclusion: NO.MS will illuminate questions related to MS characterisation, progression and prognosis. Age modulates relapse frequency and, thus, the phenotypic presentation of MS. Disease worsening across all phenotypes is mediated by age and appears to some extent be independent from new focal inflammatory activity.

Background: The expanded disability status scale (EDSS) is the standard clinical outcome measure in primary progressive multiple sclerosis (PPMS), even though the timed 25-foot walk (T25FW), nine-hole peg test (NHPT) or combinations of these measures may be more useful. The paced auditory serial addition test (PASAT) is a widely used cognitive measure in MS, but little is known about change in PASAT scores over time in PPMS. Objective: The objective of this study is to compare clinical outcome measures in a large PPMS trial data set. Methods: We determined significant worsening events on the EDSS, T25FW and NHPT, and PASAT scores over the course of this 3-year trial. We compared unconfirmed, confirmed and sustained disability worsening and contrasted disability worsening with similarly defined improvement. We examined the association of baseline characteristics with the risk of disability worsening at 12, 24 and 36 months with logistic regression models. Results: The EDSS and T25FW showed most worsening events, while only few patients worsened on the NHPT. Adding the NHPT to a combined outcome added only few further worsening events. PASAT scores slightly increased over time, possibly due to a practice effect. Conclusion: Both the EDSS and T25FW, but not NHPT or PASAT, appear to be useful outcome measures in PPMS.

It is of vital importance to identify the pleural line when performing lung ultrasound, as the pleural line not only indicates the interface between the chest wall and lung, but offers additional diagnostic information. In the current clinical practice, the pleural line is visually detected and evaluated by clinicians, which requires experiences and skills with challenges for the novice. In this study, we developed a computer-aided technique for automated pleural line detection using ultrasound. The method first utilized the Radon transform to detect line objects in the ultrasound images. The relation of the body mass index and chest wall thickness was then applied to estimate the range of the pleural thickness, based on which the pleural line was detected together with the consideration of the ultrasonic properties of the pleural line. The proposed method was validated by testing 83 ultrasound data sets collected from 21 pneumothorax patients. The pleural lines were successfully identified in 76 data sets by the automated method (successful detection rate 91.6%). In those successful cases, the depths of the pleural lines measured by the automated method agreed with those manually measured as confirmed with the Bland-Altman test. The measurement errors were below 5% in terms of the pleural line depth. As a conclusion, the proposed method could detect the pleural line in an automated manner in the defined data set. In addition, the method may potentially act as an alternative to visual inspection after further tests on more diverse data sets are performed in future studies.

In this article, I discuss construction of a set of weighted indices for the Minnesota Multiphasic Personality Inventory-2 Restructured Form (MMPI-2-RF) designed to provide direct guidance in three specific differential diagnostic problems. I created a calibration data set using a combined sample of mental health patients ( n = 2,043). Using the MMPI-2-RF’s Substantive Scales as a pool of potential predictors, I applied the lasso, a penalized regression technique, to derive three logistic regression equations differentiating three major diagnostic groups (schizophrenia, bipolar disorder, and major depressive disorder) from one another. Then, I extracted empirically derived beta weights from these equations and used them to create composite differential diagnostic indices, which I scored in a separate holdout validation data set ( n = 873). The differential diagnostic indices performed well in the validation data set (schizophrenia vs. bipolar area under the curve [AUC] = .76; schizophrenia vs. major depression AUC = .90; bipolar vs. major depression AUC = .75). Moreover, they substantially outperformed any single existing MMPI-2-RF scale in the same differential diagnostic tasks. In addition to discussing the development and initial validation of these indices, I present methods for deriving clinically referenced standard scores and diagnostic classification probabilities for obtained raw index scores.

Machine learning (ML) models based on a large data set of in-cylinder flow fields of an IC engine obtained by high-speed particle image velocimetry allow the identification of relevant flow structures underlying cycle-to-cycle variations of engine performance. To this end, deep feature learning is employed to train ML models that predict cycles of high and low in-cylinder maximum pressure. Deep convolutional autoencoders are self-supervised-trained to encode flow field features in low dimensional latent space. Without the limitations ascribable to manual feature engineering, ML models based on these learned features are able to classify high energy cycles already from the flow field during late intake and the compression stroke as early as 290 crank angle degrees before top dead center ([Formula: see text]) with a mean accuracy above chance level. The prediction accuracy from [Formula: see text] to [Formula: see text] is comparable to baseline ML approaches utilizing an extensive set of engineered features. Relevant flow structures in the compression stroke are revealed by feature analysis of ML models and are interpreted using conditional averaged flow quantities. This analysis unveils the importance of the horizontal velocity component of in-cylinder flows in predicting engine performance. Combining deep learning and conventional flow analysis techniques promises to be a powerful tool for ultimately revealing high-level flow features relevant to the prediction of cycle-to-cycle variations and further engine optimization.

This research investigates the email features that make a phishing email difficult to detect by humans. We use an existing data set of phishing and ham emails and expand that data set by collecting annotations of the features that make the emails phishing. Using the new, annotated data set, we perform cluster analyses to identify the categories of emails and their attributes. We then analyze the accuracy of detection in each category. Our results indicate that the similarity of the features of phishing emails to benign emails, play a critical role in the accuracy of detection. The phishing emails that are most similar to ham emails had the lowest accuracy while the phishing emails that were most dissimilar to the ham emails were detected more accurately. Regression models reveal the contribution of phishing email’s features to phishing detection accuracy. We discuss the implications of these results to theory and practice.

This article analyses various patterns in the pollution levels of [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text] at various locations in Kolkata, India. Our analysis is based on a data set recorded by the Central Pollution Control Board of India and the West Bengal Pollution Control Board, comprising of about 15 years of irregular time series observations, due to the higher cost of precise and accurate measurements of pollution. We perform some exploratory analysis concerning the variations in trend, seasonal, and shift-specific seasonal levels. As well as a statistical model for forecasting pollution levels for two to three days in advance is also obtained, along with an analysis of the effects of festivities such as Kali Puja and Diwali on the level of the pollutants across different locations.

In many experiments and especially in translational and preclinical research, sample sizes are (very) small. In addition, data designs are often high dimensional, i.e. more dependent than independent replications of the trial are observed. The present paper discusses the applicability of max t-test-type statistics (multiple contrast tests) in high-dimensional designs (repeated measures or multivariate) with small sample sizes. A randomization-based approach is developed to approximate the distribution of the maximum statistic. Extensive simulation studies confirm that the new method is particularly suitable for analyzing data sets with small sample sizes. A real data set illustrates the application of the methods.

In this paper, we consider variable selection for ultra-high dimensional quantile regression model with missing data and measurement errors in covariates. Specifically, we correct the bias in the loss function caused by measurement error by applying the orthogonal quantile regression approach and remove the bias caused by missing data using the inverse probability weighting. A nonconvex Atan penalized estimation method is proposed for simultaneous variable selection and estimation. With the proper choice of the regularization parameter and under some relaxed conditions, we show that the proposed estimate enjoys the oracle properties. The choice of smoothing parameters is also discussed. The performance of the proposed variable selection procedure is assessed by Monte Carlo simulation studies. We further demonstrate the proposed procedure with a breast cancer data set.

Fractional flow reserve is the current reference standard in the assessment of the functional impact of a stenosis in coronary heart disease. In this study, three models of artificial intelligence of varying degrees of complexity were compared to fractional flow reserve measurements. The three models are the multivariate polynomial regression, which is a statistical method used primarily for correlation; the feed-forward neural network; and the long short-term memory, which is a type of recurrent neural network that is suited to modelling sequences. The models were initially trained using a virtual patient database that was generated from a validated one-dimensional physics-based model. The feed-forward neural network performed the best for all test cases considered, which were a single vessel case from a virtual patient database, a multi-vessel network from a virtual patient database, and 25 clinically invasive fractional flow reserve measurements from real patients. The feed-forward neural network model achieved around 99% diagnostic accuracy in both tests involving virtual patients, and a respectable 72% diagnostic accuracy when compared to the invasive fractional flow reserve measurements. The multivariate polynomial regression model performed well in the single vessel case, but struggled on network cases as the variation of input features was much larger. The long short-term memory performed well for the single vessel cases, but tended to have a bias towards a positive fractional flow reserve prediction for the virtual multi-vessel case, and for the patient cases. Overall, the feed-forward neural network shows promise in successfully predicting fractional flow reserve in real patients, and could be a viable option if trained using a large enough data set of real patients.

In practice, it is common to evaluate biomarkers in binary classification settings (e.g. non-cancer vs. cancer) where one or both main classes involve multiple subclasses. For example, non-cancer class might consist of healthy subjects and benign cases, while cancer class might consist of subjects at early and late stages. The standard practice is pooling within each main class, i.e. all non-cancer subclasses are pooled together to create a control group, and all cancer subclasses are pooled together to create a case group. Based on the pooled data, the area under ROC curve ( AUC) and other characteristics are estimated under binary classification for the purpose of biomarker evaluation. Despite the popularity of this pooling strategy in practice, its validity and implication in biomarker evaluation have never been carefully inspected. This paper aims to demonstrate that pooling strategy can be seriously misleading in biomarker evaluation. Furthermore, we present a new diagnostic framework as well as new accuracy measures appropriate for biomaker evaluation under such settings. In the end, an ovarian cancer data set is analyzed.

We develop a ground motion prediction equation (GMPE) for estimating horizontal ground motion amplitudes caused by crustal earthquakes, based on an integrated data set that includes strong motion recordings mainly from Taiwan earthquakes and only from large magnitude earthquakes in the NGA-West2 database. This GMPE is developed for probabilistic seismic hazard analysis study, which is introduced as a part of Taiwan Senior Seismic Hazard Analysis Committee Level 3 projects. The functional form developed by Chiou and Youngs was carefully studied to determine the key modeling parameters needed to regress against ground motion in the target region. Using this functional form, the GMPE achieves considerable improvement over previously developed Taiwan GMPEs. In particular, the use of a high-order function in magnitude scaling enables representation of the saturation effects of large earthquakes. Moreover, consideration of focal mechanisms, depth effects, and dip effects are used to correct the magnitude scaling; consideration of nonlinear site amplification is conditioned on VS30and reference ground motion on rock; and consideration of basin depth effect is a function of Z1.0in correlation with VS30. In addition, ground motion data used in this study are not only expanded by more than three times as many earthquakes and records compared with a previous Taiwan model but also provide the metadata of these records that were not available or were previously incomplete. In this study, we compare the proposed model with the NGA-West2 models and discuss the regional difference in ground motion in terms of spectral shape, magnitude scaling, distance scaling, depth scaling, style of faulting, and site effects. We provide median and single standard deviations of peak ground acceleration and 5% damped pseudospectral acceleration response ordinates of the orientation-independent average horizontal component of ground motion (RotD50) for the spectral period of 0.01–10 s.

The consumer online search journey is viewed as one of the key determinants toward consumer purchase decisions. Using a unique disaggregated query-level data set collected from a leading Chinese search engine, we employ a latent-class, two-stage logistic regression model and identify the existence of three distinct consumer segments in the hospitality industry. Each group represents a unique stage of the consumer experience along a typical search journey, leading to a set of click-through behaviors. The consumer search and click-through insights garnered from this study provide hotel marketers with deeper understandings and actionable guidelines to the development of their search advertising campaign and (re)targeting strategies. The segmentation model and the empirical insights also demonstrate the possibility that a segment-specific ad assortment approach could improve advertising efficiency, enrich consumer’s search experience, and eventually create a win-win situation that benefit all entities involved in the hospitality-related, search advertising domain.

As a method to derive a “purified” measure along a dimension of interest from response data that are potentially multidimensional in nature, the projective item response theory (PIRT) approach requires first fitting a multidimensional item response theory (MIRT) model to the data before projecting onto a dimension of interest. This study aims to explore how accurate the PIRT results are when the estimated MIRT model is misspecified. Specifically, we focus on using a (potentially misspecified) two-dimensional (2D)-MIRT for projection because of its advantages, including interpretability, identifiability, and computational stability, over higher dimensional models. Two large simulation studies (I and II) were conducted. Both studies examined whether the fitting of a 2D-MIRT is sufficient to recover the PIRT parameters when multiple nuisance dimensions exist in the test items, which were generated, respectively, under compensatory MIRT and bifactor models. Various factors were manipulated, including sample size, test length, latent factor correlation, and number of nuisance dimensions. The results from simulation studies I and II showed that the PIRT was overall robust to a misspecified 2D-MIRT. Smaller third and fourth simulation studies were done to evaluate recovery of the PIRT model parameters when the correctly specified higher dimensional MIRT or bifactor model was fitted with the response data. In addition, a real data set was used to illustrate the robustness of PIRT.

This paper introduces the newly developed principal component powered two-dimensional (2D) correlation spectroscopy (PC 2D-COS) as an alternative approach to 2D correlation spectroscopy taking advantage of a dimensionality reduction by principal component analysis. It is shown that PC 2D-COS is equivalent to traditional 2D correlation analysis while providing a significant advantage in terms of computational complexity and memory consumption. These features allow for an easy calculation of 2D correlation spectra even for data sets with very high spectral resolution or a parallel analysis of multiple data sets of 2D correlation spectra. Along with this reduction in complexity, PC 2D-COS offers a significant noise rejection property by limiting the set of principal components used for the 2D correlation calculation. As an example for the application of truncated PC 2D-COS a temperature-dependent Raman spectroscopic data set of a fullerene-anthracene adduct is examined. It is demonstrated that a large reduction in computational cost is possible without loss of relevant information, even for complex real world data sets.

In this commentary, we welcome Schimmack’s reanalysis of Bar-Anan and Vianello’s multitrait multimethod (MTMM) data set, and we highlight some limitations of both the original and the secondary analyses. We note that when testing the fit of a confirmatory model to a data set, theoretical justifications for the choices of the measures to include in the model and how to construct the model improve the informational value of the results. We show that making different, theory-driven specification choices leads to different results and conclusions than those reported by Schimmack (this issue, p. 396). Therefore, Schimmack’s reanalyses of our data are insufficient to cast doubt on the Implicit Association Test (IAT) as a measure of automatic judgment. We note other reasons why the validation of the IAT is still incomplete but conclude that, currently, the IAT is the best available candidate for measuring automatic judgment at the person level.

Based on the data set from Chinese Industrial Enterprises Database (2003–2008), this article first quantifies the net job creation of industrial enterprises in China by three methods: the base-year method ( Birch, 1979 ), the average-year method ( Davis, Haltiwanger, & Schuh, 1996 ) and the dynamic method (Davidsson, 1998). After evaluating from the results, it is concluded that the dynamic method is more precise than others. By adapting the dynamic method to the database, this article reaffirms that small and medium enterprises (SMEs) in China are the dominated power in terms of job creation. Furthermore, relationships between net job creation and several enterprise characteristics, including enterprise size, age, average salary and asset are investigated with the data calculated by the dynamic method. Instead of conventional linear regressions, a lognormal simulation is found to be more suitable to describe those relationships. Finally, the conclusion in this article indicates that not only the SMEs but also young enterprises (under the age of 5) are the major force in creating jobs in China.

Survey research frequently involves the collection of data from multiple informants. Results, however, are usually analyzed by informant group, potentially ignoring important relationships across groups. When the same construct(s) are measured, integrative data analysis (IDA) allows pooling of data from multiple sources into one data set to examine information from multiple perspectives within the same analysis. Here, the IDA procedure is demonstrated via the examination of pooled data from student and teacher school climate surveys. This study contributes to the sparse literature regarding IDA applications in the social sciences, specifically in education. It also lays the groundwork for future educational researchers interested in the practical applications of the IDA framework to empirical data sets with complex model structures.

We present a data set of ground motion recordings and site information from vertical array sites in California. The recordings include two horizontal components of ground shaking at the ground surface level and from downhole sensors. The availability of both surface and downhole recordings at the same site facilitates direct observations of site response. The site data include measured shear-and compression-wave velocities, and, where available, geotechnical boring logs. We considered 39 vertical array sites in California and chose 21 for inclusion in the database on the basis of having at least four pairs of surface/downhole recordings. The recordings and site data are presented in a data repository, which is accessible at the DesignSafe platform (DOI: 10.17603/146DS2N680). The original digital accelerograms are processed in a manner consistent with NGA-West2 protocols. In this paper, this data set is compared to a similar but larger data set from Japanese vertical arrays compiled by others.

Objectives. Uncertainty in survival prediction beyond trial follow-up is highly influential in cost-effectiveness analyses of oncology products. This research provides an empirical evaluation of the accuracy of alternative methods and recommendations for their implementation. Methods. Mature (15-year) survival data were reconstructed from a published database study for “no treatment,” radiotherapy, surgery plus radiotherapy, and surgery in early stage non–small cell lung cancer in an elderly patient population. Censored data sets were created from these data to simulate immature trial data (for 1- to 10-year follow-up). A second data set with mature (9-year) survival data for no treatment was used to extrapolate the predictions from models fitted to the first data set. Six methodological approaches were used to fit models to the simulated data and extrapolate beyond trial follow-up. Model performance was evaluated by comparing the relative difference in mean survival estimates and the absolute error in the difference in mean survival v. the control with those from the original mature survival data set. Results. Model performance depended on the treatment comparison scenario. All models performed reasonably well when there was a small short-term treatment effect, with the Bayesian model coping better with shorter follow-up times. However, in other scenarios, the most flexible Bayesian model that could be estimated in practice appeared to fit the data less well than the models that used the external data separately. Where there was a large treatment effect (hazard ratio = 0.4), models that used external data separately performed best. Conclusions. Models that directly use mature external data can improve the accuracy of survival predictions. Recommendations on modeling strategies are made for different treatment benefit scenarios.

A novel technique of detecting DIF in items using z-score based on IRT model. A simple technique based on z-score is proposed and derived for Rasch Model and also compared with traditional DIF detection methods. The data set used for application is the State Level Achievement Survey data set from West Bengal, India. Binary responses on 40-item tests of 12518 examinees are taken.

A preventive measure for debonding has not been established and is highly desirable to improve the survival rate of computer-aided design/computer-aided manufacturing (CAD/CAM) composite resin (CR) crowns. The aim of this study was to assess the usefulness of deep learning with a convolution neural network (CNN) method to predict the debonding probability of CAD/CAM CR crowns from 2-dimensional images captured from 3-dimensional (3D) stereolithography models of a die scanned by a 3D oral scanner. All cases of CAD/CAM CR crowns were manufactured from April 2014 to November 2015 at the Division of Prosthodontics, Osaka University Dental Hospital (Ethical Review Board at Osaka University, approval H27-E11). The data set consisted of a total of 24 cases: 12 trouble-free and 12 debonding as known labels. A total of 8,640 images were randomly divided into 6,480 training and validation images and 2,160 test images. Deep learning with a CNN method was conducted to develop a learning model to predict the debonding probability. The prediction accuracy, precision, recall, F-measure, receiver operating characteristic, and area under the curve of the learning model were assessed for the test images. Also, the mean calculation time was measured during the prediction for the test images. The prediction accuracy, precision, recall, and F-measure values of deep learning with a CNN method for the prediction of the debonding probability were 98.5%, 97.0%, 100%, and 0.985, respectively. The mean calculation time was 2 ms/step for 2,160 test images. The area under the curve was 0.998. Artificial intelligence (AI) technology—that is, the deep learning with a CNN method established in this study—demonstrated considerably good performance in terms of predicting the debonding probability of a CAD/CAM CR crown with 3D stereolithography models of a die scanned from patients.

The Semantic Web allows knowledge discovery on graph-based data sets and facilitates answering complex queries that are extremely difficult to achieve using traditional database approaches. Intuitively, the Semantic Web query language (SPARQL) has a ‘property path’ feature that enables knowledge discovery in a knowledgebase using its reasoning engine. In this article, we utilise the property path of SPARQL and the other Semantic Web technologies to answer sophisticated queries posed over a disease data set. To this aim, we transform data from a disease web portal to a graph-based data set by designing an ontology, present a template to define the queries and provide a set of conjunctive queries on the data set. We illustrate how the reasoning engine of ‘property path’ feature of SPARQL can retrieve the results from the designed knowledgebase. The results of this study were verified by two domain experts as well as authors’ manual exploration on the disease web portal.

This article introduces an extended data set of 760 terrorist groups that engaged in attacks during 1970 to 2016. Unlike most extant group data sets, the extended data on terrorist groups (EDTG) is not tied to terrorist groups and attacks listed in the RAND terrorism data; rather, EDTG is linked to terrorist groups and attacks given in the Global Terrorism Database. Terrorist groups’ variables in EDTG include ideology, main goals, start date, duration, base country, attack diversity, peak size, alternative endings (if relevant), and others. We display interesting features of EDTG through a series of tables and figures. Our EDTG-based survival analysis is at odds with some of the literature: for example, the demise of a leader and a larger share of transnational terrorist attacks increase the group’s odds of failure. After 2001, religious terrorist groups are more resilient than those with other ideologies. We also analyze terrorist group lethality and productivity.

We propose a penalized variable selection method for the Cox proportional hazards model with interval censored data. It conducts a penalized nonparametric maximum likelihood estimation with an adaptive lasso penalty, which can be implemented through a penalized EM algorithm. The method is proven to enjoy the desirable oracle property. We also extend the method to left truncated and interval censored data. Our simulation studies show that the method possesses the oracle property in samples of modest sizes and outperforms available existing approaches in many of the operating characteristics. An application to a dental caries data set illustrates the method's utility.

This paper presents the development of large-scale simulation-based data sets used to inform new site amplification models for Central and Eastern North America (CENA). Linear elastic, equivalent linear, and nonlinear one-dimensional site response simulations of site conditions in CENA are employed. An analysis tree is introduced to capture the range of expected CENA geologic conditions. Independent variables include the following: (1) representative and random shear wave velocity ( VS) profiles using data from the literature; (2) randomized, nonlinear shear modulus reduction and damping vs. shear strain curves with constraint on soil shear strength; and (3) outcrop ground motions representative of the VS= 3,000 m/s CENA reference rock condition. The resulting database of 1,747,278 simulations is conditioned on several parameters relevant to site amplification, which facilitates model development that is the subject of a companion paper. The database is openly available for use by other researchers.

Free-text information is still widely used in emergency department (ED) records. Machine learning techniques are useful for analyzing narratives, but they have been used mostly for English-language data sets. Considering such a framework, the performance of an ML classification task of a Spanish-language ED visits database was tested. ED visits collected in the EDs of nine hospitals in Nicaragua were analyzed. Spanish-language, free-text discharge diagnoses were considered in the analysis. Five-hundred random forests were trained on a set of bootstrap samples of the whole data set (1,789 ED visits) to perform the classification task. For each one, after having identified optimal parameter value, the final validated model was trained on the whole bootstrapped data set and tested. The classification accuracies had a median of 0.783 (95% CI [0.779, 0.796]). Machine learning techniques seemed to be a promising opportunity for the exploitation of unstructured information reported in ED records in low- and middle-income Spanish-speaking countries.

Cosmic ray artifacts may be present in all photo-electric readout systems. In spectroscopy, they present as random unidirectional sharp spikes that distort spectra and may have an affect on post-processing, possibly affecting the results of multivariate statistical classification. A number of methods have previously been proposed to remove cosmic ray artifacts from spectra but the goal of removing the artifacts while making no other change to the underlying spectrum is challenging. One of the most successful and commonly applied methods for the removal of comic ray artifacts involves the capture of two sequential spectra that are compared in order to identify spikes. The disadvantage of this approach is that at least two recordings are necessary, which may be problematic for dynamically changing spectra, and which can reduce the signal-to-noise (S/N) ratio when compared with a single recording of equivalent duration due to the inclusion of two instances of read noise. In this paper, a cosmic ray artefact removal algorithm is proposed that works in a similar way to the double acquisition method but requires only a single capture, so long as a data set of similar spectra is available. The method employs normalized covariance in order to identify a similar spectrum in the data set, from which a direct comparison reveals the presence of cosmic ray artifacts, which are then replaced with the corresponding values from the matching spectrum. The advantage of the proposed method over the double acquisition method is investigated in the context of the S/N ratio and is applied to various data sets of Raman spectra recorded from biological cells.

To perform computer-aided diagnosis of the thyroid nodules on ultrasound images, the location and boundary of nodules should be clearly defined. However, the identification of thyroid nodule boundary is a difficult issue due to the biological characteristics of the nodules, the physics and quality of ultrasound imaging, and the subjective factors and operating conditions of the operator. In this study, we propose a novel and semiautomatic method for detecting the boundary of thyroid nodule based on the Variance-Reduction (V-R) statistics without image preprocessing. The region of interest (ROI) is first automatically generated according to the initial inputs of the nodule's major and minor axes. The boundary candidate pixel points are then extracted by using the V-R statistics from the grayscale values of all pixel points in the ROI. Three filtering methods are further applied to eliminate the outlier pixel points to ensure that the remaining candidate pixel points are located on the nodule boundary. Finally, the remaining pixel points are smoothened and linked together to form the final boundary. The proposed method is validated with ultrasound images of 538 thyroid nodules, with manual delineation by experienced radiologist as gold standard. The effectiveness is evaluated and compared with previous publications using boundary error metrics and overlapping area metrics with the same data set. The results show that the normalized average mean boundary error is 1.02%, the true positive overlapping area ratio achieves 93.66% and false positive overlapping area ratio is limited to 7.68%. In conclusion, our proposed method is reliable and effective in detecting thyroid nodule boundary on ultrasound images.

Data visualizations typically show a representation of a data set with little to no focus on the repeatability or generalizability of the displayed trends and patterns. However, insights gleaned from these visualizations are often used as the basis for decisions about future events. Visualizations of retrospective data therefore often serve as “visual predictive models.” However, this visual predictive model approach can lead to invalid inferences. In this article, we describe an approach to visual model validation called Inline Replication. Inline Replication is closely related to the statistical techniques of bootstrap sampling and cross-validation and, like those methods, provides a non-parametric and broadly applicable technique for assessing the variance of findings from visualizations. This article describes the overall Inline Replication process and outlines how it can be integrated into both traditional and emerging “big data” visualization pipelines. It also provides examples of how Inline Replication can be integrated into common visualization techniques such as bar charts and linear regression lines. Results from an empirical evaluation of the technique and two prototype Inline Replication–based visual analysis systems are also described. The empirical evaluation demonstrates the impact of Inline Replication under different conditions, showing that both (1) the level of partitioning and (2) the approach to aggregation have a major influence over its behavior. The results highlight the trade-offs in choosing Inline Replication parameters but suggest that using [Formula: see text] partitions is a reasonable default.

With the advent of modern cognitive computing technologies, fashion informatics researchers contribute to the academic and professional discussion about how a large-scale data set is able to reshape the fashion industry. Data-mining-based social network analysis is a promising area of fashion informatics to investigate relations and information flow among fashion units. By adopting this pragmatic approach, we provide dynamic network visualizations of the case of Paris Fashion Week. Three time periods were researched to monitor the formulation and mobilization of social media users’ discussions of the event. Initial textual data on social media were crawled, converted, calculated, and visualized by Python and Gephi. The most influential nodes (hashtags) that function as junctions and the distinct hashtag communities were identified and represented visually as graphs. The relations between the contextual clusters and the role of junctions in linking these clusters were investigated and interpreted.

When making decisions, people tend to choose the option they have looked at more. An unanswered question is how attention influences the choice process: whether it amplifies the subjective value of the looked-at option or instead adds a constant, value-independent bias. To address this, we examined choice data from six eye-tracking studies ( Ns = 39, 44, 44, 36, 20, and 45, respectively) to characterize the interaction between value and gaze in the choice process. We found that the summed values of the options influenced response times in every data set and the gaze-choice correlation in most data sets, in line with an amplifying role of attention in the choice process. Our results suggest that this amplifying effect is more pronounced in tasks using large sets of familiar stimuli, compared with tasks using small sets of learned stimuli.

The current study seeks to compare 3 clustering algorithms that can be used in gene-based bioinformatics research to understand disease networks, protein-protein interaction networks, and gene expression data. Denclue, Fuzzy-C, and Balanced Iterative and Clustering using Hierarchies (BIRCH) were the 3 gene-based clustering algorithms selected. These algorithms were explored in relation to the subfield of bioinformatics that analyzes omics data, which include but are not limited to genomics, proteomics, metagenomics, transcriptomics, and metabolomics data. The objective was to compare the efficacy of the 3 algorithms and determine their strength and drawbacks. Result of the review showed that unlike Denclue and Fuzzy-C which are more efficient in handling noisy data, BIRCH can handle data set with outliers and have a better time complexity.

When information and measures obtained from sequences of microscopic images are subject to time constraints, suitable fast algorithms must be implemented to process the whole data set. In this work, we deal with sequences of images obtained from time-lapse microscopy in order to detect single yeast cells in a microfluidics chip over time. The underlying idea consists in determining a minimum cost configuration for each couple of frames, which can be expressed by setting up and solving a linear programming (LP) problem. Laboratories seldom have the opportunity to use HPC hardware for such intent. For this reason, we propose an efficient GPU-parallel software implemented in CUDA and based on the simplex method, a common tool for solving LP problems. Our parallel strategy minimizes the threads divergence and maximizes the device occupancy, in order to maximize the overall throughput. Also, memory transfers between host and device have been minimized to exploit data locality. Experimental results on real images sequences highlight a promising speedup with respect to the CPU version suitable for real-time applications.

Several facial expression image sets have been developed. Nevertheless, there is a lack of facial expression sets comprising adolescents’ images depicting all basic emotions. This study aimed to fill this gap through the development of an image database of youth facial expressions, containing pictures of six basic emotions plus neutral. Posed and spontaneous expressions were collected from 31 youths, 12 to 20 years old; 2,279 frames were obtained, and an initial screening was conducted through the exclusion of similar frames, low intensity images, and ambiguous or blended expressions; 256 frames met criteria and were rechecked by two expert judges. Images were retained if they depicted all the prototypical features of the designated expression. A final selection was conducted to assure an image set that covered all age ranges, both sexes and an even number of images by expression, resulting in 42 frames (21 male, six of each emotion). Expert judges, independent adults, independent teenagers, and a software validation were used to assure database validity. Agreement across raters was high, and no differences were observed for posed and spontaneous images. The data set developed in this study can be a valid tool in studies of facial expressions, in particular, with adolescents’ samples.

Exploratory factor analysis is a statistical method commonly used in psychological research to investigate latent variables and to develop questionnaires. Although such self-report questionnaires are prone to missing values, there is not much literature on this topic with regard to exploratory factor analysis—and especially the process of factor retention. Determining the correct number of factors is crucial for the analysis, yet little is known about how to deal with missingness in this process. Therefore, in a simulation study, six missing data methods (an expectation–maximization algorithm, predictive mean matching, Bayesian regression, random forest imputation, complete case analysis, and pairwise complete observations) were compared with respect to the accuracy of the parallel analysis chosen as retention criterion. Data were simulated for correlated and uncorrelated factor structures with two, four, or six factors; 12, 24, or 48 variables; 250, 500, or 1,000 observations and three different missing data mechanisms. Two different procedures combining multiply imputed data sets were tested. The results showed that no missing data method was always superior, yet random forest imputation performed best for the majority of conditions—in particular when parallel analysis was applied to the averaged correlation matrix rather than to each imputed data set separately. Complete case analysis and pairwise complete observations were often inferior to multiple imputation.

Several gene- or set-based association tests have been proposed recently in the literature. Powerful statistical approaches are still highly desirable in this area. In this paper we propose a novel statistical association test, which uses information of the burden component and its complement from the genotypes. This new test statistic has a simple null distribution, which is a special and simplified variance-gamma distribution, and its p-value can be easily calculated. Through a comprehensive simulation study, we show that the new test can control type I error rate and has superior detecting power compared with some popular existing methods. We also apply the new approach to a real data set; the results demonstrate that this test is promising.

This article investigates the work of processors who curate and “clean” the data sets that researchers submit to data archives for archiving and further dissemination. Based on ethnographic fieldwork conducted at the data processing unit of a major US social science data archive, I investigate how these data processors work, under which status, and how they contribute to data sharing. This article presents two main results. First, it contributes to the study of invisible technicians in science by showing that the same procedures can make technical work invisible outside and visible inside the archive, to allow peer review and quality control. Second, this article contributes to the social study of scientific data sharing, by showing that the organization of data processing directly stems from the conception that the archive promotes of a valid data set—that is, a data set that must look “pristine” at the end of its processing. After critically interrogating this notion of pristineness, I show how it perpetuates a misleading conception of data as “raw” instead of acknowledging the important contribution of data processors to data sharing and social science.

This study examines the determinants of men’s exit from female-dominated occupations. Using census data and the National Longitudinal Survey of Youth data set, the author analyzes the job history of men employed in the United States between 1979 and 2006. Supporting the theoretical model, evidence indicates a group of stopgappers—men entering female-dominated occupations and leaving soon after their entry, thereby contributing to the perpetuation of segregation in female settings. By identifying the stopgapper occupational trajectory, this article contributes to the development of a comprehensive theory accounting for the way structural inequality is reproduced.

The recommendation of using “multiple measures” is common in policy guidelines for gifted and talented assessment systems. However, the integration of multiple test scores in a system that uses cut-scores requires choosing between different methods of combining quantitative scores. Past research has indicated that OR combination rules (where any one score must meet the cutoff) have been shown to identify the largest number of students compared with AND (where all scores must meet cutoff) and AVERAGE (where the numerical average is used) rules. We extended this work to a real data set (Grades K to 5 from the CogAT 7 national standardization data) and found that the different combination rules led to differences in the number and diversity of students identified. However, we found these diversity differences were due mainly to the identified pool size and not to the effects of the particular combination rule. This has important implications for practice.