scholarly journals Interdependency Pattern Recognition in Econometrics: A Penalized Regularization Antidote

Econometrics ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 44
Author(s):  
Kimon Ntotsis ◽  
Alex Karagrigoriou ◽  
Andreas Artemiou
Keyword(s):  
Pattern Recognition ◽  
Data Analytics ◽  
Model Misspecification ◽  
Big Data Analytics ◽  
Real Data ◽  
Information Criterion ◽  
Information Complexity ◽  
Model Assessment ◽  
New Era ◽  
Proper Interpretation

When it comes to variable interpretation, multicollinearity is among the biggest issues that must be surmounted, especially in this new era of Big Data Analytics. Since even moderate size multicollinearity can prevent proper interpretation, special diagnostics must be recommended and implemented for identification purposes. Nonetheless, in the areas of econometrics and statistics, among other fields, these diagnostics are controversial concerning their “successfulness”. It has been remarked that they frequently fail to do proper model assessment due to information complexity, resulting in model misspecification. This work proposes and investigates a robust and easily interpretable methodology, termed Elastic Information Criterion, capable of capturing multicollinearity rather accurately and effectively and thus providing a proper model assessment. The performance is investigated via simulated and real data.

AusGeochem and Big Data Analytics in Low-Temperature Thermochronology

2021 ◽  
Author(s):  
Samuel Boone ◽  
Fabian Kohlmann ◽  
Moritz Theile ◽  
Wayne Noble ◽  
Barry Kohn ◽  
...  
Keyword(s):  
Big Data ◽  
Low Temperature ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Application Programming Interface ◽  
Large Datasets ◽  
Geochemical Data ◽  
Advisory Group ◽  
New Era ◽  
Analytical Instruments

<p>The AuScope Geochemistry Network (AGN) and partners Lithodat Pty Ltd are developing AusGeochem, a novel cloud-based platform for Australian-produced geochemistry data from around the globe. The open platform will allow laboratories to upload, archive, disseminate and publish their datasets, as well as perform statistical analyses and data synthesis within the context of large volumes of publicly funded geochemical data. As part of this endeavour, representatives from four Australian low-temperature thermochronology laboratories (University of Melbourne, University of Adelaide, Curtin University and University of Queensland) are advising the AGN and Lithodat on the development of low-temperature thermochronology (LTT)-specific data models for the relational AusGeochem database and its international counterpart, LithoSurfer. These schemas will facilitate the structured archiving of a wide variety of thermochronology data, enabling geoscientists to readily perform LTT Big Data analytics and gain new insights into the thermo-tectonic evolution of Earth’s crust.</p><p>Adopting established international data reporting best practices, the LTT expert advisory group has designed database schemas for the fission track and (U-Th-Sm)/He methods, as well as for thermal history modelling results and metadata. In addition to recording the parameters required for LTT analyses, the schemas include fields for reference material results and error reporting, allowing AusGeochem users to independently perform QA/QC on data archived in the database. Development of scripts for the automated upload of data directly from analytical instruments into AusGeochem using its open-source Application Programming Interface are currently under way.</p><p>The advent of a LTT relational database heralds the beginning of a new era of Big Data analytics in the field of low-temperature thermochronology. By methodically archiving detailed LTT (meta-)data in structured schemas, intractably large datasets comprising 1000s of analyses produced by numerous laboratories can be readily interrogated in new and powerful ways. These include rapid derivation of inter-data relationships, facilitating on-the-fly age computation, statistical analysis and data visualisation. With the detailed LTT data stored in relational schemas, measurements can then be re-calculated and re-modelled using user-defined constants and kinetic algorithms. This enables analyses determined using different parameters to be equated and compared across regional- to global scales.</p><p>The development of this novel tool heralds the beginning of a new era of structured Big Data in the field of low-temperature thermochronology, improving laboratories’ ability to manage and share their data in alignment with FAIR data principles while enabling analysts to readily interrogate intractably large datasets in new and powerful ways.</p>

scholarly journals Studying Cloud as IaaS for Big Data Analytics : Opportunity, Challenges

2018 ◽  
Vol 7 (2.7) ◽  
pp. 909
Author(s):  
Amitkumar Manekar ◽  
Dr Pradeepini Gera
Keyword(s):  
Cloud Computing ◽  
Big Data ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Cloud Infrastructure ◽  
Computational Framework ◽  
New Era ◽  
Post Process ◽  
James Watt ◽  
Data Ecosystem

James Watt steam engine revolution was greatest revolution in mankind history in 20th century. In 1776, the first steam engines were installed and working in commercial enterprises. This revolution minimize and make world smaller for human being, now world is connected seamlessly. “Big Data Analytics and Cloud” these two words are second numerous revolutions in 21st century.  We are living in an era of information explosion. These two magical terms are nothing but relatively very new and fortunately diverted all market trends to a new era of computation in last decade. As these two emerging technology are their early childhood, many people were confused with its relevancy and applicability. Cloud Computing is Infrastructure based solution for managing data and computational framework. 2016 was a significantly more important year for this volumes data technology or Big Data eco system as large number of enterprises, and organizations are generating data, storing that data and worried about future aspect of that data. In 2017, corporate world take cognizance of their large volumes structured and unstructured data as these enterprises and organizations continuously generating large volumes data. The term big data doesn’t just refer to the massive amounts of data existing today, it also refers to the whole ecosystem of Storing or gathering data, Different types of data and analyzing that data. In traditional data ecosystem all leverages are with legacy system.  Transforming or migration of these traditional ecosystems to the cloud is full of great challenges and benefits. Cloud computing is an agile and scalable resource access computation paradigm, provides heterogeneous platform seamlessly with infrastructure of internet, exclusively for the trapped and work on pre and post process of big data. Now the challenges are finding opportunity and challenges for managing, migrating and abstracting cloud based big data using cloud infrastructure for future eco system of Big Data Analysis.  This paper is basically focused on this issue. We try to reevaluate the facts of existing Cloud Infrastructure as IaaS for tomorrow’s big data analytics.    

Overview of Big Data and Its Visualization

2022 ◽  
pp. 22-53
Author(s):  
Richard S. Segall ◽  
Gao Niu
Keyword(s):  
Big Data ◽  
Traffic Safety ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Real Data ◽  
Flow Diagram ◽  
Data Sets ◽  
United States Department ◽  
Big Data Visualization ◽  
Challenges And Opportunities

Big Data is data sets that are so voluminous and complex that traditional data processing application software are inadequate to deal with them. This chapter discusses what Big Data is and its characteristics, and how this information revolution of Big Data is transforming our lives and the new technology and methodologies that have been developed to process data of these huge dimensionalities. This chapter discusses the components of the Big Data stack interface, categories of Big Data analytics software and platforms, descriptions of the top 20 Big Data analytics software. Big Data visualization techniques are discussed with real data from fatality analysis reporting system (FARS) managed by National Highway Traffic Safety Administration (NHTSA) of the United States Department of Transportation. Big Data web-based visualization software are discussed that are both JavaScript-based and user-interface-based. This chapter also discusses the challenges and opportunities of using Big Data and presents a flow diagram of the 30 chapters within this handbook.

scholarly journals Eco-Innovation and Industry 4.0: A Big Data Usage conceptual model

2018 ◽  
Vol 56 ◽  
pp. 05003 ◽  
Author(s):  
Russell Tatenda Munodawafa ◽  
Satirenjit Kaur Johl
Keyword(s):  
Big Data ◽  
Industry 4.0 ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Digital Economy ◽  
Future Research ◽  
New Era ◽  
Data Usage ◽  
The World ◽  
Development Goals

Driven by Cyber Physical Systems, Big Data Analytics, Internet of Things and Automation, Industry 4.0 is expected to revolutionize the world. A new era beckons for enterprises of all sizes, markets, governments, and the world at large as the digital economy fully takes off under Industry 4.0. The United Nations has also expressed its desire to usher in a new era for humanity with the Sustainable Development Goals 2030 (SDG’s) replacing the Millennial Development Goals (MDG’s). Critical to the achievement of both of the above-mentioned ambitions is the efficient and sustainable use of natural resources. Big Data Analytics, an important arm of Industry 4.0, gives organizations the ability to eco-innovate from a resource perspective. This paper conducts an analysis of previously published research literature and contributes to this emerging research area looking at Big Data Usage from a strategic and organizational perspective. A conceptual framework that can be utilized in future research is developed from the literature. Also discussed is the expected impact of Big Data Usage towards firm performance, particularly as the world becomes more concerned about the environment. Data driven eco-innovation should be in full motion if organizations are to remain relevant in tomorrow’s potentially ultra-competitive digital economy.

Overview of Big Data and Its Visualization

2018 ◽  
pp. 1-32 ◽  
Author(s):  
Richard S. Segall ◽  
Gao Niu
Keyword(s):  
Big Data ◽  
Traffic Safety ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Real Data ◽  
Flow Diagram ◽  
Data Sets ◽  
United States Department ◽  
Big Data Visualization ◽  
Challenges And Opportunities

Big Data is data sets that are so voluminous and complex that traditional data processing application software are inadequate to deal with them. This chapter discusses what Big Data is and its characteristics, and how this information revolution of Big Data is transforming our lives and the new technology and methodologies that have been developed to process data of these huge dimensionalities. This chapter discusses the components of the Big Data stack interface, categories of Big Data analytics software and platforms, descriptions of the top 20 Big Data analytics software. Big Data visualization techniques are discussed with real data from fatality analysis reporting system (FARS) managed by National Highway Traffic Safety Administration (NHTSA) of the United States Department of Transportation. Big Data web-based visualization software are discussed that are both JavaScript-based and user-interface-based. This chapter also discusses the challenges and opportunities of using Big Data and presents a flow diagram of the 30 chapters within this handbook.

Sign in / Sign up

Export Citation Format

Share Document