Free special issue on stochastic modelling in business and industry

News

  • Author: Ron Kenett and Galit Shmueli
  • Date: 26 February 2015

Applied Stochastic Models in Business and Industry (ASMBI) was first published in 1985, and has since been publishing contributions in the interface between stochastic modeling, data analysis and their application in business, finance, insurance, management and production. The journal’s main objective is to publish application-focused papers, both technical and practical, presenting new results which solve real-life problems or have great potential in doing so. Domains of such problems include reliability, quality control, forecasting, managerial decision making, database management, and more. A second objective is to present new methods for solving such problems, including optimization, database management, knowledge acquisition, expert systems, decision support systems and neural computing, managerial processes, reliability, quality control, data analysis and data mining. A third objective is to present new methodologies for solving real-life problems, including new methods in optimization, simulation, probability models, statistical analysis, visualization, and data mining.

thumbnail image: Free special issue on stochastic modelling in business and industry

The January/February 2015 issue of ASMBI is a special issue on actual impact and future perspectives on stochastic modelling in business and industry and will be free to read throughout 2015. It consists of six invited papers by prominent statisticians who cover a range of topics providing a broad perspective on the current and future role of stochastic and statistical modelling in business and industry. Each paper is also addressed by a discussant who has been asked to present additional perspectives, thereby expanding the scope of each topic. The combination of paper and discussion, and breadth of topics, is aimed at providing the reader with a comprehensive exchange of thoughts and ideas.

Four papers focus on methods and applications, including testing of mega-systems such as Google, scalable decision trees that optimize response time in recommendation systems, degradation models used in reliability analysis, and advanced experimental design models. The scope of these papers maps wide territories with huge opportunities for current and future contributions to and from statistics. Two more papers provide a general view of the role of statistics in national labs and creativity centers. These hand-picked contributions are designed to expand the scope of traditional statistical research and stimulate a lifecycle approach with measurable impact combining explanatory and predictive studies and an emphasis on providing quality information from data (Shmueli, 2010, Kenett, 2014, Kenett and Shmueli, 2014).

Specifically, the papers included in this issue are:
1. Opportunities to Empower Statisticians in Emerging Areas by Christine Anderson-Cook, with discussion by Ron Snee
2. Stochastic modeling and analysis of degradation for highly reliable products by Zhisheng Ye and Min Xie with discussion by Paul Kvam
3. Multi-armed bandit experiments in the online service economy by Steven Scott with discussion by Deepak Agarwal
4. Alternatives to Resolution III Regular Fractional Factorial Designs for 9 – 14 Factors in 16 Runs by Shilpa Shinde, Brad Jones, and Doug Montgomery with discussion by David Steinberg
5. Parallel Construction of Decision Trees with Consistently Non-Increasing Expected Number of Tests by Irad Ben-Gal and Chavazelet Trister with discussion by Jean Michel Poggi
6. (sfi)² Statistics for Innovation – the experience of the Oslo centre in industrial statistics by Arnoldo Frigessi and André Teigland with discussion by David Banks.

Specifically, in the first paper, Anderson-Cook presents opportunities to expand the impact and influence of statistics by considering statistics within an application area rather than as an isolated set of data analysis tools. The author illustrates the opportunities via several examples from collaborative projects under way at Los Alamos National Laboratory in the USA. The closing paper by Frigessi and Teigland describes a national initiative to boost multidisciplinary innovative research in Norway. The other four papers look at specific methodologies and application developments. Ye and Xie survey the landscape of degradation of highly reliable products, a topic of high relevance to modern industry. The paper by Scott describes the use of multi-armed bandit experiments in online applications for improving usability by considering actual user experiences. The paper by Shinde, Jones and Montgomery describes alternatives to a type of experimental designs that are both efficient and adaptable experimental strategies. The paper by Ben-Gal and Trister looks at decision trees, a popular machine learning technique, taking a perspective combining utility and performance, thus enhancing algorithmic utility when considering chronology of data and goal.

This combination of methodological and application domains alongside discussions on the role of statisticians and statistics, serves to sketch the important role of statistics and statistical research in the context of various new developments such as data science, big data, analytics and machine learning. It shows that the field of statistics is both about strategy and methods in every application domain where structured and unstructured data is used to achieve scientific or practical goals.

There is currently consensus and some alarm in the statistics community about the field of statistics being challenged by other disciplines in leading “data science” and “data analytics”. Is the role of statistics limited to theoretical developments that form the basis for data analysis? Are these methods applied to contemporary applications? And how does statistical thinking contribute to the application of data analytic methods in practice? The papers in this special issue, together with their follow up discussions, show that the field of statistics is an important contributor to a wider scope of areas of interest, starting from strategy and the role of innovation, to machine learning and modern big data problems. To keep and expand this view, statistics must embrace a life cycle view and develop methods for evaluating and enhancing the quality of generated information (Kenett and Shmueli, 2014, Kenett, 2014). Presenting such needs and expectations from the statistics profession will hopefully lead researchers to develop new methods and tools for achieving these objectives. Moreover, the ability to make a difference requires fast adaptation to new application areas and good communication with non-statisticians. It seems that we will also see a growing involvement of statisticians in new areas of interdisciplinary work – another skill and capability that has become a requirement for statisticians with implications to statistical education and research methods. The fast changing environment creates many opportunities that the statistics community must cease. As Jerzy Neyman used to say: “life is complicated but not uninteresting”. For statistics these are definitely interesting times.

References

Kenett, R.S. and Shmueli G. (2014), On information quality. Journal of the Royal Statistical Society, Series A (Statistics in Society), vol. 177, issue 1, pp. 3-27.
Kenett, R.S. (2014), Statistics: A Life Cycle View, Quality Engineering, Vol. 27, No.1, pp. 11-121, 2014.
Shmueli, G (2010), To explain or to predict?, Statistical Science, Vol. 25, pp. 289–310.

Related Topics

Related Publications

Related Content

Site Footer

Address:

This website is provided by John Wiley & Sons Limited, The Atrium, Southern Gate, Chichester, West Sussex PO19 8SQ (Company No: 00641132, VAT No: 376766987)

Published features on StatisticsViews.com are checked for statistical accuracy by a panel from the European Network for Business and Industrial Statistics (ENBIS)   to whom Wiley and StatisticsViews.com express their gratitude. This panel are: Ron Kenett, David Steinberg, Shirley Coleman, Irena Ograjenšek, Fabrizio Ruggeri, Rainer Göb, Philippe Castagliola, Xavier Tort-Martorell, Bart De Ketelaere, Antonio Pievatolo, Martina Vandebroek, Lance Mitchell, Gilbert Saporta, Helmut Waldl and Stelios Psarakis.