Different Levels Of Data Aggregation Research Articles

An integrated individual-level trait-based phytoplankton dataset from transitional waters

Functional trait-based approaches have undergone an extraordinary expansion in phytoplankton ecology. Morpho-functional traits have been shown to vary both within and between populations and species, potentially affecting individual fitness and the network of inter-individual relationships. Here we integrate six fully harmonized phytoplankton morpho-functional trait datasets, characterized by a fine data grain, reporting individual-level data over a large biogeographical area. Datasets refer to transitional water ecosystems, from five biogeographical areas: Northern Atlantic Ocean (Scotland), South-Western Atlantic Ocean (Brazil), South-Western Pacific Ocean (Australia), Indo Pacific Ocean (Maldives) and Mediterranean Sea (Greece and Turkey). The integrated dataset includes 127311 individual phytoplankton records with sampling locations, taxonomic and morphometric information according to Darwin Core standards and semantic annotations. The six FAIR datasets are openly available in the LifeWatch Italy data portal. The datasets have already been used for morpho-functional analyses and hypothesis testing on phytoplankton guilds at different levels of data aggregation and scale, from local to global.

Are you ready for retirement? The influence of values on membership in voluntary organizations in midlife and old age.

Membership in voluntary organizations is associated with individual and social benefits. Due to the negative consequences of the global pandemic on older people, and the governmental challenges posed by population aging, voluntary membership is of great importance to society. To effectively promote volunteering among older people, it is necessary to understand the determinants of voluntary membership. This study analyses the influence of individual values—secular/traditional and survival/self-expression–on voluntary membership among European adults (N = 31,985). Specifically, it examines which values orient two age groups (middle age: 50–64 and old age: 65–79), as well as men and women toward a certain type of association (Social Awareness; Professional and Political; Education and Leisure; Religion). The sample of 31,985 comprises 60% of adults aged 50–64 and 40% aged 65–79; of which 56% are women and 44% men. The empirical estimation considers different levels of data aggregation: individual, national and welfare system, therefore multilevel analysis is used as an analytical strategy. Individual-level variables from the Integrated Values Survey (2005/09, 2010/14, and 2017/20) and national-level variables (Gini Index and Gross Domestic Product Per Capita) from the World Bank and Eurostat are used. The results indicate that traditional and self-expression values promote membership in voluntary organizations in general more than secular and survival values. However, there are differences according to the type of organization. Furthermore, values are found to moderate the effect of age and gender on voluntary membership.

Competitiveness of the Regions of the European Union in a Sustainable Knowledge-Based Economy

The aim of the article is to analyze the level of the knowledge-based economy (KBE) in the European Union countries in terms of sustainable development. The added value of the work is the presentation of research results at different levels of data aggregation (EU countries, EU macro-regions, EU regions). This type of approach was used for the first time in this study. The research assumes that knowledge and skills are one of the basic factors in implementing the concept of sustainable development. Currently, there are very large disproportions at the level of KBE in the countries, macro-regions, and regions of the EU. It also translates into their socio-economic situation and thus into competitiveness and innovation. The highest level of KBE is in north-western and central Europe countries, while the lowest is in the countries of eastern and south-eastern Europe. This regularity also applies to macro-regions and regions located in these countries.

The Influence of Gender Equality on Volunteering Among European Senior Citizens

This research analyzes how gender equality influences the participation of European senior citizens in a range of volunteering activities (Social Awareness, Professional and Political, Education, and Religion). The main contribution is the simultaneous consideration of different levels of data aggregation: individual, national and welfare system. This allows conclusions to be drawn on the effects of variables linked to sociodemographic characteristics, gender equality and welfare systems. The empirical estimation utilised microdata from the World Values Survey (2005/09 and 2010/14) and the United Nations Development Programme. Results suggest that the European senior citizens appear to believe that they are more equal than the official statistics of their countries indicate. Men are more likely to participate in professional and education activities; women are more likely to be involved in religious organisations. Welfare systems influence volunteering behaviours. The promotion of macro-policies for gender equality could be important for increasing participation in non-profit organisations.

Regional per capita income differences: Spatial and hierarchical dependencies

Relevance. Regional differences in per capita income are a matter of concern for many countries for many reasons, including the threat that such regional disparities pose to national security. Multiple tools and methods are used to investigate these disparities and fix them. The use of lower level aggregated data and the analysis that takes into account spatial interactions thus become particularly relevant because it allows us to reveal the diversity of interactions at the micro-level. Research objective. This study aims to determine the significance of spatial relationships at different levels of data aggregation and hierarchical dependencies in per capita income and highlight the level of administrative division (regional or municipal) that has the greatest impact on per capita income. Methods and data. The analysis relies on the data from 2,270 municipalities in 85 Russian regions. The Hierarchical Spatial Autoregressive Model (HSAR) was used to distinguish both spatial and hierarchical effects. We used three specifications of the model: with estimates of the spatial interaction on the higher level (spatial error at the regional level), on the lower level (spatial lag at the municipal level), and on both levels. Results. Spatial interactions explain the observed variation of per capita income at the municipal level data at both the higher (regional) and lower (municipal) levels but the model with the estimated spatial interaction on the higher level was better. Conclusion. Despite the importance of spatial interactions at the lower level, models that take into account spatial interactions only at the upper level may better explain the observed differences in some cases. Our findings contribute to the rather scarce research literature on spatial relationships on several levels of administrative division. We have shown that for each specific case it is important to identify not only the factors but also the spatial effects in relation to this or that level of the territorial hierarchy.

The forensics of fraud: Evidence from the 2018 Brazilian presidential election

ObjectiveThis paper studies the integrity of the vote counting system in Brazil. MethodWe analyze data from the Superior Electoral Court (TSE) for the 2018 Brazilian presidential election to assess suspicious vote count patterns deploying five techniques commonly used to detect fraud: a) the second-digit Benford's law test; b) the last digit mean; c) frequency analysis of last digits 0 and 5; d) correlation between the percentage of votes and the turnout rate; and e) resampled Kernel density of the proportion of votes. ResultsThe results show that the second-digit distributions for the three most voted candidates – Jair Messias Bolsonaro (PSL), Fernando Haddad (PT), and Ciro Gomes (PDT) – conform to Benford's law. We also find that last digit means and last digit frequency are within normal parameters, indicating no irregularities. Similarly, the fingerprint plot indicates a correlation coefficient that is consistent with the theoretical expectation of a fair election. The resampled Kernel density suggests that the vote count was performed without statistically significant distortions. These results are robust at different levels of data aggregation (polling station and municipality). ConclusionThe joint application of digit-focused tests, regression-based techniques, and patterns in the distribution of vote-shares provide a more reliable method for detecting anomalous cases. Relying on this unified framework, we find no evidence of electoral fraud in the 2018 Brazilian presidential election. These results advance our current understanding of statistical forensics tools and may be easily replicated to examine electoral integrity in other countries.

Longitudinal analyses suggest a higher burden of self-reported influenza-like illness among women and girls in a rural community in western Kenya

Longitudinal studies that quantify influenza-like illness (ILI) burden while determining associated risk factors and intra-cluster correlation coefficients (ICCs) are scarce in Africa. This study aimed to identify longitudinal patterns of ILI and the associated independent variables while quantifying the burden by age and sex. We enrolled and followed 390 subjects nested within 92 households for 12 weeks, collecting weekly data on prespecified self-reported symptoms in a rural community in western Kenya. Using a standard case definition, reporting at least any four prespecified symptoms attained an ILI syndrome. Analyses related relationship between attaining ILI syndrome and independent variables using multilevel logistic regression models adjusting for age and sex. ICCs quantified clustering of ILI syndrome computed at different levels of data aggregation. Of the 4261 reports received, 592 (14%) registered an illness, with 278 (48%) of these attaining ILI syndrome. The 278 reports belonged to 176 (41%) subjects dwelling in 76 (83%) households. On average, each study subject and household experienced 1.6 and 3.7 episodes of ILI syndrome, respectively. Making a visit outside the local area of residence (Odds ratio (OR) =2.7, 95% CI 1.8, 4.1) and living in a cement-floored house (OR = 1.9, 95% CI 1.1, 3.3) independently predicted attaining ILI syndrome. Correcting for the population structure revealed an excess risk of 16% in attaining the syndrome among the study women and girls. Clustering of ILI syndrome was lowest at the individual level (ICC = 0.04) and slightly higher within households (ICC = 0.14), suggesting moderate household contextual influences. Regardless of the cause, we provide evidence of a potentially higher ILI syndrome burden among women and girls in our study area. Studies are needed to establish granular exposures defining the increasing risk of ILI syndrome associated with gender, making a visit outside the local sub-county of residence and living in a cement-floored house.

Gaze-angle dependency of pupil-size measurements in head-mounted eye tracking

Pupillometry - the study of temporal changes in pupil diameter as a function of external light stimuli or cognitive processing - requires the accurate and gaze-angle independent measurement of pupil dilation. Expected response amplitudes often are only a few percent relative to a pre-stimulus baseline, thus demanding for sub-millimeter accuracy. Video-based approaches to pupil-size measurement aim at inferring pupil dilation from eye images alone. Eyeball rotation in relation to the recording camera as well as optical effects due to refraction at corneal interfaces can, however, induce so-called pupil foreshortening errors (PFE), i.e. systematic gaze-angle dependent changes of apparent pupil size that are on a par with typical response amplitudes. While PFE and options for its correction have been discussed for remote eye trackers, for head-mounted eye trackers such an assessment is still lacking. In this work, we therefore gauge the extent of PFE in three measurement techniques, all based on eye images recorded with a single near-eye camera. We present both real world experimental data as well as results obtained on synthetically generated eye images. We discuss PFE effects at three different levels of data aggregation: the sample, subject, and population level. In particular, we show that a recently proposed refraction-aware approach employing a mathematical 3D eye model is successful in providing pupil-size measurements which are gaze-angle independent at the population level.

Multiscale and Multivariate Transportation System Visualization for Shopping District Traffic and Regional Traffic

In this paper, we present a suite of visualization techniques for sensor-based transportation system data at different scales to facilitate the exploration of interconnected traffic dynamics at intersections and highways. These techniques are designed for analyzing multivariate traffic data from radar-based highway sensors and camera-based intersection sensors recording turn movements and vehicle speed, in the Chattanooga Metropolitan Area, with the capability of (a) revealing multiscale mobility patterns using different levels of data aggregation (e.g., individual sensor for microscale, multiple sensors along a corridor for mesoscale, and a larger number of sensors across the region for macroscale visualization) at different intervals (e.g., 5-min intervals, time of day, full day, and day-of-the-week), and (b) exploring the spatial variation of multiple traffic-related variables (e.g., volumes, speeds, turn movements, and traffic light colors) provided by the sensors. We close with a case study to demonstrate the effectiveness of our multiscale and multivariate visualization techniques. At microscale, we focused on intersection data from a shopping district around Shallowford Road in East Chattanooga. For mesoscale visualization, we studied the Shallowford Road corridor and an adjacent stretch of I-75. At macroscale, we included highway data from the Chattanooga Metropolitan Area. All visualizations were integrated into a web-based situational awareness tool to promote user access and interaction. At a minimum, each visualization provides the option for selecting dates for real-time (depending on sensor availability) and historical data, and additional information on hovering, though most provide more detailed information, including different views of the selected data, or interactive highlights.

Aggregation of condition survey data in pavement management: shortcomings of a homogeneous sections approach and how to avoid them

A common feature of most pavement management systems is the aggregation of condition data collected from periodic surveys to appropriate long homogeneous sections, aiming to reduce the amount of data to be analysed. It can be shown that regardless of the methods used for sectioning and prediction, homogeneous sections cannot describe the true variation in condition and failure time, leading to either over- or underestimation of service life and hence suboptimal selection of timing and type of maintenance and rehabilitation (M&R) treatments. Furthermore, the generation of homogeneous sections hinders the derivation of project-level performance models from historical condition surveys due to shifting of sections and greatly reduces the number of possible work-zone solutions in the optimisation. This paper illustrates the deviations resulting from different levels of data aggregation based on a case study of 1000 road sections. The results of common sectioning algorithms are then compared to those derived from a LCC-optimisation approach based on accurate condition predictions on short survey sections and work-zones based on economies of scale. The conclusions of this work may be useful to road agencies in avoiding substantial drawbacks of data aggregation and improving project-level M&R treatment recommendations based on the same input condition data.

A Permissioned Distributed Ledger for the US Beef Cattle Supply Chain

Distributed ledgers using blockchain have gained traction in the supply chain industry due to their unique features of immutability and transparency. They have given people the abilities to solve business problems which were impossible using traditional systems. The US beef cattle industry lacks adequate traceability as most of the farm owners consider such data confidential; possibly harming their businesses if exposed. This article attempts to solve this problem by proposing a smart contract-based supply chain framework using a permissioned blockchain network. This system supports anonymity for the users to protect identities and lets every user store their data locally, while ensuring that the changes are recorded in the chain with cryptographic proofs (hashes). The proposed framework also has methods for the users to perform business transactions and transfer animal-related data to new owners as required. In addition to that, smart contracts have been added to conduct anonymous surveys for data aggregation. The technical contribution of this article is in the system design on how users, data, and communications are handled to maintain data ownership and user privacy while ensuring immutability and confidentiality at different levels of data aggregation. This article also contains an evaluation of the system using integration tests where the outcomes meet the expected design requirements. The framework can be applied to the US beef cattle industry as well as other supply chains with minimal modifications.

Estimating IBNR claim counts using different levels of data aggregation

Reserving problem in non-life insurance is an applied statistical problem with several computational aspects. In the literature, the focus has mainly been on aggregate reserving techniques and the chain-ladder method with its extensions has remained as the most widely applied claim reserving method. The classical chain-ladder method is regularly applied to annual data, but the question arises whether the reserve estimates based on more refined data outperform results obtained by annual data. We investigate whether and how much different data aggregation levels can improve the reserving process. To compare the performance of the classical chain-ladder method and its novel continuous extension, we conduct two simulation studies as well as a case study with an insurance data and use both models to estimate the IBNR claim count estimates on different levels of data aggregation. The results demonstrate that the continuous approach of the chain-ladder method provides in general a minor improvement in the IBNR predictions but proves to hold its predictive power on different types of data. This study highlights data aggregation levels in which the estimates of classical chain-ladder model outperforms the estimates obtained by the use of annual data, providing more insights for establishing accurate loss reserves.

Capacity planning in supply chains of mineral resources

The paper addresses the existing gap in the literature on the optimisation in capacity planning for mineral supply chains. The presented optimisation procedure aims at minimising the cost of infrastructure expansion for any given scenario of future demand. The optimisation procedure is designed as a matheuristic – a hybridisation of mixed integer linear programming (MILP), and a simulated annealing based scheduler. The optimisation procedure is iterative in nature and has the following distinctive features. Each iteration starts with generating a MILP model and finding a minimal cost infrastructure expansion for this model. Then, the scheduler analyses the MILP solution by constructing a schedule. In constructing this schedule, the scheduler reduces its search space using the MILP solution. The scheduler identifies bottlenecks in the infrastructure, which are used for generating a new MILP model at the next iteration. The MILP and the scheduler use different levels of data aggregation and their interaction mechanism is designed as a solution process of a bi-criteria optimisation problem. The computational experiments on data, originating from the world’s largest coal exporter, shows the ability of the developed matheuristic to solve industrial-scaled instances of the problem.

A comprehensive evacuation planning model and genetic solution algorithm

We consider the problem of evacuating an urban area. Several planning aspects need to be considered in such a scenario, which are usually considered separately. We propose a macroscopic multi-criteria optimization model that includes several such questions simultaneously, and develop a genetic algorithm to solve the problem heuristically. Its applicability is extended by also considering how to aggregate instance data, and how to generate solutions for the original instance starting from a reduced solution. In computational experiments using real-world data, we demonstrate the effectiveness of our approach and compare different levels of data aggregation.

Voluntary Work in Europe: Comparative Analysis Among Countries and Welfare Systems

The main contribution of this paper to the research of volunteering participation is considering simultaneously different levels of data aggregation: individual, country and welfare regimen. This strategy allows us identifying individual factors (socio-demographic variables) and contextual data (government expenditures on social issues and GDP), as well as comparing different political backgrounds (welfare systems). Our results suggest that socio-demographic characteristics and contextual data are important predictors of volunteer rates. Macro-policies might be effective tools to promote national volunteering participation, because international differences on volunteer rates smooth with the introduction of national contextual data.

Power laws and comparative advantage

Using a comprehensive international trade data set we document empirical Power Laws (PLs) for the distribution of the interaction between countries as measured by revealed comparative advantage. Using the recently developed estimator by Gabaix and Ibragimov (2011), we find strong evidence in favour of PLs along the time, country and sector dimension for three different levels of data aggregation. This finding is not predicted by any of the existing trade theories. The estimated PL exponents characterizing the distribution of revealed comparative advantage are stable over time but differ between countries and sectors. These differences are related empirically to country and sector characteristics, including population size, Gross Domestic Product (GDP) and factor intensities.

Supply chain design under uncertainty using sample average approximation and dual decomposition

We present a supply chain design problem modeled as a sequence of splitting and combining processes. We formulate the problem as a two-stage stochastic program. The first-stage decisions are strategic location decisions, whereas the second stage consists of operational decisions. The objective is to minimize the sum of investment costs and expected costs of operating the supply chain. In particular the model emphasizes the importance of operational flexibility when making strategic decisions. For that reason short-term uncertainty is considered as well as long-term uncertainty. The real-world case used to illustrate the model is from the Norwegian meat industry. We solve the problem by sample average approximation in combination with dual decomposition. Computational results are presented for different sample sizes and different levels of data aggregation in the second stage.

Using stock assessment information to assess fishing capacity of tuna fisheries

Abstract Arrizabalaga, H., Restrepo, V. R., Maunder, M. N., and Majkowski, J. 2009. Using stock assessment information to assess fishing capacity of tuna fisheries. – ICES Journal of Marine Science, 66: 1959–1966. In tuna and tuna-like fisheries, there is a need for periodic assessments of fishing capacity to aid management. However, the nature and quantity of data needed to apply conventional methodologies for estimating fishing capacity are not usually available for tuna fisheries. We discuss simple alternative approaches to estimate fishing capacity and related quantities (i.e. capacity utilization, excess capacity, and overcapacity) directly from stock assessment inputs and outputs that are usually available for most tuna (and many other) stocks. Sensitivity analyses are performed to assess the effect of different levels of data aggregation and different assumptions made during the stock assessments on estimates of fishing capacity. Main advantages and disadvantages of the proposed methodologies are also illustrated using stock assessment information from different tuna stocks with different historical developments and trends in fishing mortality.

Measuring urban polycentrism: a European case study and its implications

New models of urban structures have emerged based on the assumption that metropolitan areas are increasingly decentralized, central business districts becoming less important in terms of employment and new subcentres emerging at the edge of cities. This article presents a method of identifying subcentres in suburban areas. This method is then applied to the question of whether subcentres exist on the periphery of medium-sized European cities and, if so, what kind of activities are located there. This is done by empirically describing and explaining the spatial structure of four urban regions in Belgium. Several spatial analysis techniques are used at different levels of data aggregation. Local autocorrelation is particularly appropriate for detecting clusters of employment, while shift-and-share analyses are useful for looking at the developmental trends. We show that, despite an overall trend to decentralization, polycentrism is still weak.

Brand personality and human personality: Findings from ratings of familiar Croatian brands

The present article focuses on two main problems: determining the factor structure of personality ratings of familiar Croatian brands and determining how different levels of data aggregation can affect the dimensionality and the nature of extracted factors. Following Aaker's seminal study [Aaker, J. Dimensions of brand personality. Journal of Marketing Research 1997; 24: 347–356], which aims to identify the dimensions of brand personality, this study attempts to relate brand personality to personality dimensions derived from the natural language. In the first study, a sample of 55 students rate the familiarity of 111 brands represented in the categories of “a Croatian creation” and “Croatian quality”. Subsequently, ten brands are selected on the basis of mean familiarity and representation in various product categories (food, beverages, medicine and cleaning products). In the second study, an exhaustive Croatian taxonomy of personality descriptors [Mlačić B, Ostendorf F. Taxonomy and Structure of Croatian Personality-descriptive Adjectives. European Journal of Personality 2005; 19: 117–152] serves as a basis for the construction of a 90-item inventory that covers the 45 facets from the AB5C model [Goldberg LR. International Personality Item Pool. A Scientific Collaboratory for the Development of Advanced Measures of Personality and Other Individual Differences. 6 June 2005. 20 April 2005. http://ipip.ori.org/ipip/]. A large sample of students (267) rate the personality of the ten selected brands using the 90-item inventory. The results of exploratory factor analyses of brand personality are discussed in respect of previous research, the lexical approach, and the possible effects of different levels of data aggregation on the dimensionality of the obtained factor structure.