PEMA's focus covers four broad areas of analytics research:
Amsler, C., James, R., Prokhorov, A., Schmidt, P. (2023). Improving Predictions of Technical Inefficiency. Advances in Econometrics, in press.
Tran, K., Tsionas, M., Prokhorov, A. (2023). Semiparametric Estimation of Spatial Autoregressive Smooth-Coefficient Panel Stochastic Frontier Models. European Journal of Operational Research, 304(3), 1189-1199.
Campbell, D., Grant, A., & Thorp, S. (2022). Reducing credit card delinquency using repayment reminders. Journal of Banking and Finance, 142, 106549
Mamonov, M., Parmeter, C., Prokhorov, A. (2022). Dependence Modeling in Stochastic Frontier Analysis. Dependence Modeling, 10(1), 123-144.
Christodoulou, D., Samuell, D., Slonim, R., Tausch, F. (2022). Counteracting dishonesty strategies: A field experiment in life insurance underwriting. Journal of Behavioral Decision Making, in press.
Zhai, T., James, R., Prokhorov, A. (2022). Technical and allocative inefficiency in production systems: a vine copula approach. Dependence Modeling, 10(1), 145-158.
Merkert, R. (2022). The impact of engine standardization on the cost efficiency of airlines. Research in Transportation Business & Management, Published online: 25 February 2022, 100797.
Merkert, R., Hakim, M. (2022). Travel agency transaction costs in airline value chains - A risk in distribution channels in South Asia? Annals of Tourism Research, 95, 103414.
Grant, A., Johnstone, D., & Kwon, O. K. (2021). A cumulative prospect theory explanation of gamblers cashing-out. Journal of Mathematical Psychology, 102, 102534
Amsler, C., Prokhorov, A., Schmidt, P. (2021). A new family of copulas, with application to estimation of a production frontier system. Journal of Productivity Analysis, 55(1), 1-14.
Prokhorov, A., Tran, K., Tsionas, M. (2021). Estimation of semi- and nonparametric stochastic frontier models with endogenous regressors. Empirical Economics, 60(6), 3043-3068.
Christodoulou, D., Samuell, D. (2020). The adviser effect on insurance disclosures. Applied Economics, 52(5), 519-527.
Peng, Z., Johnstone, D., Christodoulou, D. (2020). Asymmetric impact of earnings news on investor uncertainty. Journal of Business Finance and Accounting, 47(1-2), 3-26. [
Merkert, R., Bushell, J. (2020). Managing the drone revolution: A systematic literature review into the current use of airborne drones and future strategic directions for their effective control. Journal of Air Transport Management, 89, 101929.
Grant, A., & Deer, L. (2020). Consumer marketplace lending in Australia: Credit scores and loan funding success. Australian Journal of Management, 45, 607–623.
Grant, A., Johnstone, D., & Kwon, O. K. (2019). The cost of capital in a prediction market. International Journal of Forecasting, 35, 313–320.
Hakim, M., Merkert, R. (2019). Econometric evidence on the determinants of air transport in South Asian countries. Transport Policy, 83, 120-126.
Christodoulou, D., Ma, L., Vasnev, A. (2018). Inference-in-residuals as an Estimation Method for Earnings Management. Abacus, 54(2), 154-180.
Christodoulou, D., Lev, B., Ma, L. (2018). The productivity of Chinese patents: The role of business area and ownership type. International Journal of Production Economics, 199, 107-124.
Matsypura, D., Thomspon, R., Vasnev, A. (2018). Optimal Selection of Expert Forecasts with Integer Programming. Omega, 78, 165-175.
Hao, B., Prokhorov, A., Qian, H. (2018). Moment redundancy test with application to efficiency-improving copulas. Economics Letters, 171, 29-33.
Grant, A., Malloch, H., & Satchell, S. (2018). The value of momentum to active managers and planned sponsors in Australia. The Australasian Journal of Applied Finance, 1, 4–10.
Matsypura, D., Prokopyev, O., Zahar, A. (2018). Wildfire fuel management: network-based models and optimization of prescribed burning. European Journal of Operational Research, 264(2), 774-796.
Merkert, R., Mulley, C., Hakim, M. (2018). Trade-offs between transaction cost, operation cost and innovation in the context of procurement and asset specificity - The example of the bus industry. Research in Transportation Economics, 69, 173-179.
Grant, A., Oikonomidis, A., Bruce, A. C., & Johnson, J. E. V. (2018). New entry, strategic diversity and efficiency in soccer betting markets: The creation and suppression of arbitrage opportunities. European Journal of Finance, 24, 1799–1816.
Christodoulou, D., Sarafidis, V. (2017). Regression clustering for panel data models with fixed effects. Stata Journal, 17(2), 314-329.
Merkert, R., Van de Voorde, E., de Wit, J. (2017). Making or breaking - Key success factors in the air cargo market. Journal of Air Transport Management, 61, 1-5.
Bradrania, R., Grant, A., Westerholm, P. J., & Wu, W. (2017). Fool's mate: What does CHESS tell us about individual investor trading performance? Accounting and Finance, 57, 981–1017
Amsler, C., Prokhorov, A., Schmidt, P. (2017). Endogenous environmental variables in stochastic frontier models. Journal of Econometrics, 199(2), 131-140.
Gudmundsson, S.V., Merkert, R. and Redondi, R. (2017). Cost functions and determinants of unit cost effects in horizontal airline M&As, Transportation Research Part A. Policy and Practice, 103, 444-54.
Prokhorov, A. (2024). Efficiency and Productivity Analysis: Using Copulas in Stochastic Frontier Models. United Kingdom: Routledge. [More Information]
Merkert, R., Bushell, J. (2021). The Future of Air Transport. In R. Vickerman (Eds.), International Encyclopedia of Transportation, (pp. 203-207). New York, USA: Elsevier.
Satchell, S., & Grant, A. (Eds.). (2021). Market momentum: Theory and practice. Chichester, UK: Wiley.
Merkert, R. (2020). Air transport in regional, rural and remote areas. In L. Budd, S. Ison (Eds.), Air Transport Management: An International Perspective (2nd ed.), (pp. 357-372). Abingdon: Routledge.
Merkert, R., Bushell, J. (2019). Long-distance transport service sustainability: Management and policy directions from the airline perspective. In Stanley J & Hensher D (Eds.), A Research Agenda for Transport Policy, (pp. 89-98). Cheltenham: Edward Elgar Publishing.
Ibragimov, R., Prokhorov, A. (2017). Heavy Tails and Copulas: Topics in Dependence Modelling in Economics and Finance. Singapore: World Scientific Publishing Co. Pte. Ltd.
Gillen, C., Matsypura, D., Prokopyev, O. (2017). Operations Research Techniques in Wildfire Fuel Management. In Butenko S, Pardalos PM, Shylo V (Eds.), Optimization Methods and Applications: In Honor of Ivan V. Sergienko's 80th Birthday, (pp. 119-135). Cham: Springer International Publishing.
Christodoulou, D., Samuell, D. (2020). Do advisors skew disclosures? - Journal of the Australian and New Zealand Institute of Insurance and Finance (ANZIIF).
Christodoulou, D., Grant, A., Johnstone, D. (2019). Behavioural Finance Client and Consumer Behaviour: Engagement and Decision Making - Handbook for Financial Advisers, Sydney, Australia.
Zhang, B., Deer, L., Wardrop, R., Grant, A., Garvey, K., Thorp, S., Ziegler, T., Ying, K., Xinwei, Z., Huang, Y., Gray, Y., Akhtar, S., Anthonisz, S., et al (2016). Harnessing Potential: The Asia-Pacific Alternative Finance Benchmarking Report, March 2016, (pp. 18 - 93). Sydney, Australia: KPMG.
PEMA organises research workshops, research meetings, and research seminars from world experts on data science and data analytics on measuring and analysing organizational productivity, efficiency and performance. PEMA has inherited the rich experience in workshops and events from the MEAFA research group.
Please check back for more upcoming events soon.
Title: A regularization approach to estimating inefficiency in stochastic frontier panel models
Date: Friday, 3 May 2024 11:00 am AEST
Description: The paper proposes a regularized mode estimator of unit inefficiency in a panel data context, allowing inefficiencies to vary across units and over time. This regularized estimator penalizes the likelihood function by constraining the sample average of the idiosyncratic error to zero. Extensive simulations demonstrate that the regularized conditional mode estimator outperforms existing estimators, such as the unregularized mode estimator and the conditional mean estimator, particularly for the least efficient firms.
Title: AI vs. Human: The Race in the M&A Decision-Making Process
Date: Apr 19, 2024 11:00 am AEST
Description: The paper proposes an AI approach to explore the universe of M&A opportunities and automate the M&A decision-making process. Tracing previous M&As and mining high-dimensional financial data, the AI model can accurately identify potential acquirers and targets in advance and project market reaction and synergy of M&As.
Title: Statistical Inference for Hicks–Moorsteen Productivity Indices
Date: Apr 5, 2024 11:00 am AEST
Description: The statistical framework for the Malmquist productivity index (MPI) is now well developed and emphasizes the importance of developing such a framework for its alternatives. We try to fill this gap in the literature for another popular measure, known as Hicks–Moorsteen Productivity Index (HMPI).
Title: Australian Insured Lives industry engagement workshop
Date: 7 September 2023
Description: The industry engagement workshop will brief executives of the life insurance industry industry on scope and significance of proposed Australian Insured Lives initiative. A pilot project is already under way involving the PEMA research group. The workshop is open only for life insurance industry representatives. If you would like to participate as a representative of your organisation, then please get in touch at business.pema@sydney.edu.au.
Title: Machine learning in business: methods and applications
Date: 29 May 2023
Description:This workshop outlined methods and applications of machine learning in business was co-hosted with the Time Series and Forecasting research group and the Business Finance and Banking research group. The workshop included research presentations and a discussion panel with industry experts.
Title: StataCorp lecture on Extended Regression Models (ERMs)
Date: 19 August 2019
Presenter: Chuck Huber, Associate Director of Statistical Outreach at StataCorp
Description: This lecture briefly reviewed the types of complications that ERMs can address and showed how to make inferences despite those complications.
Title: ABS DataLab training
Date: 27 March and 5 April 2018
Presenter: Talei Parker, A/g Assistant Director, Microdata Outputs and Customer Relations, Customised and Microdata Delivery Section, ABS.
Description: The training covered legal responsibilities and clearance of outputs, processes and access, as required for anyone wishing to use the ABS DataLab, the data analysis solution for high-end data users who want to extract full value from ABS microdata in an interactive (real-time) environment.
Title: IBM: Cognitive - The 3rd Era of Computing
Date: 20 Oct 2017
Presenter: Prof. Dr. Jürg von Känel
Description: A short overview of the history, and then focus on the current state of the art in showing examples of todays art of the possible using various kinds of information such as image, voice, natural language texts form short texts like tweets to long reports, and how this starts to allow to tackle problems previously not considered part of what computers can solve, from answering questions to finding pre/con arguments to analysing human personality traits. He showed that all of these are driven by the human desire to make sense of our world using data and the computer becomes an interactive assistant to the human decision maker.
Title: Jeremy Bertomeu and Edwige Cheynel masterclass on Structural Models
Date: 25 Jan 2017
Presenters: Prof Jeremy Bertomeu and Prof Edwige Cheynel
Description: This workshop outlined the theory of structural models with an emphasis on parameter identification and then discuss econometric estimators and related issues. An application on disclosure theory will follow.
Title: Google Big Query
Date: 9 Dec 2016
Presenter: Douglas Abdiel, Google Analytics 360, Asia Pacific region.
Description: A hands-on workshop on how to apply Google's infrastructure for uploading, storing, reducing, and extracting relational databases. The focus is learning to work efficiently with multi-terabyte fluid datasets using real-time computations.
Title: Oceania Stata meeting
Date: 29-30 September 2016
Presenter: StataCorp staff and presenters from academia and industry
Description: The Stata meeting is a flagship event of StataCorp and Stata users in Oceania, and was co-organised with Neuroscience Research Australia (NeuRA) and Survey Design & Analysis Services Pty Ltd. Associate Professor Demetris Christodoulou served as the chair of the Stata meeting.
Title: Prevails workshop on Text Analytics
Date: 28 September 2015
Presenter: Dr Normand Péladeau, President and founder of Provalis Research.
Description: Provalis Research is a Canadian company specialising in developing and marketing text analytics tools combining computer-assisted qualitative analysis through QDA Miner with quantitative content analysis and text-mining through WordStat. The workshop presents tools and approaches for analysing human language and text mining, including exploration of text, identifying themes, extracting topics, correspondence text analysis, dictionary construction, automated document classification and more.
Title: ABS Expo, UN World Stats Day
Date: 20 October 2015
Presenter: Associate Professor Demetris Christodoulou and Professor Artem Prokhorov
Description: World Statistics Day is a United Nations worldwide initiative for recognising the contribution statistics make in shaping societies around the world. The research group was invited to the participate in the Expo as a representative of the University of Sydney Business School. This is the headline event for World Statistics Day celebrations is the Australian Bureau of Statistics Transformation Showcase Expo, highlighting some key achievements in the ABS transformation program.
Title: Neural Networks in econometric systems
Date: 15-17 Feb 2010
Presenter: Professor Hans Georg Zimmermann, Principal Research Scientist, Siemens AG - Corporate Technology.
Description: The workshops discusses the system identification problem as mainly a learning task, including the integration of additional prior information which can be used as a pre-design of the network architecture. It shows how the modelling procedure itself can be extended instead of insisting on the model building certainties (data, priors), to measure the uncertainties and use these information to control the learning and developing closed dynamical systems.
PEMA offers professional development workshops for state-of-the-art data analytics methods. The hands-on workshops are delivered by world experts and are tailored at the executive researcher level.
PEMA's professional development workshops build on more than a decade-long experience of delivering such workshops by the now disestablished MEAFA research group. The net proceeds from PEMA's professional development workshops go to funding PhD scholarships and development research programs.
Our workshops are widely recognised by academia, private sector, state and federal governments, and non-profit organisations for their highest quality.
Please check back for more scheduled workshops soon.
Title: Machine Learning on Text Documents
Dates: 2-6 December 2019
Presenters: Alexander Semenov, Social Media Analysis Group, Faculty of Information Technology, the University of Jyvaskyla, Finland. Alexander Veremyev, Department of Industrial Engineering & Management Systems, University of Central Florida, USA
Description: Text analysis involves the process of retrieving, managing, structuring and analysing unstructured text, deriving patterns from structured data using statistical and machine learning algorithms, for evaluation and inference. In this workshop, the focus is the analysis of text documents using machine learning methods. Typical applications include finding/extracting relevant information from the text, text categorisation, document summarization, text clustering, sentiment analysis, personality analysis, concept extraction, analysis of semantic relations, and more.
Title: Text Analytics using Python
Dates: 3-7 December 2018
Presenters: Alexander Semenov, Alexander Veremyev
Description: The workshop will use the Python programming language (Anaconda distribution), and, in particular, overview the most popular machine learning and text processing libraries. Python is a programming language of choice for data scientists for manipulation, visualising and executing complex data analyses on text data.
Title: Machine Learning using Python
Dates: 19-23 February 2018
Presenters: Marcel Scharth, Dmytro Matsypura
Description: The workshop was based on the powerful ecosystem of free and open source machine learning libraries for Python. The main tool used was Scikit-Learn, a production-ready framework that provides a wide range of machine learning algorithms through implementations that are simple to use. The workshop leveraged state-of-art libraries such as XGBoost and TensorFlow for specialised tasks. Participants acquired a wide range of machine learning tools for applications in business and economics.
Title: Bayesian analysis using Stata
Dates: 5-9 February 2018
Presenters: Yulia Marchenko, Demetris Christodoulou
Description: This workshop demonstrated the use of Bayesian analysis in various applications and will introduce Stata's suite of commands for conducting Bayesian analysis.
Title: Social Media data extraction, management and analysis
Dates: 27-30 November 2017
Presenters: Alexander Semenov, Alexander Veremyev, Dmytro Matsypura.
Description: This workshop reviewed key concepts in data extraction and management, in particular, how data can be handled using relational database management systems, and understand how unstructured data from the WWW and social media can be gathered, parsed, loaded into the database, and analysed. In addition, the workshop also covered the basics of network science and its applications.
Title: Stochastic Frontier Analysis using Stata
Dates: 13-17 February 2017
Presenters: Artem Prokhorov, Demetris Christodoulou
Description: The workshops provide a thorough introduction to Stata, including Working Efficiently with Stata (Monday 13 Feb), Stata Programming (Tuesday 14 Feb), and Data Management (Wednesday 15 Feb), as well as two days on Stochastic Frontier Analysis.
Title: Panel data analysis
Date: 8-12 February 2016
Presenter: Associate Professor Vasilis Sarafidis, Department of Econometrics at Monash University
Description: This workshop lays the foundations for panel data analysis and error component models, including mixed/multilevel error error components, for developing linear, non-linear and dynamic estimation models. Applications are drawn from extensive consulting experience on panel data problems, including work with the UK Office for Water Services, Telestyrelsen Denmark, Jersey Competition Regulatory Authority, UK Electricity Association, and Sydney Water Corporation.
Title: Microeconometrics for count data
Date: 14-16 December 2015
Presenter: Professor Colin Cameron, University of California at Davis.
Description: The workshop deals with count data analysis, such as the analysis of frequency of events, such as the number of visits to a doctor, the number of accidents, the number of earthquakes, the number of new patents awarded. The focus is on microeconometrics for count data, including regression analysis and simulation-based analysis, where the dependent variable contains nonnegative integers. All methods are illustrated in by real life applications to cross-section and panel count data examples.
Title: Treatment effects
Date: 29 June - 3 July 2015
Presenter: Dr David Drukker, Director of Econometrics, StataCorp LP.
Description: This workshop focuses on causal analysis using treatment effect estimators, which measure the change in an outcome caused by a subject getting one treatment instead of another or not receiving any treatment, e.g. a patient receiving and the treatment a new drug regimen, or a worker participating in a job-training program. The key question is whether the treatment has a causal effect on an outcome. A counterfactual model specifies the potential outcomes that each individual would obtain under each treatment level, the treatment assignment process, and the dependence of the potential outcomes on the treatment assignment process.
Title: Exploratory data analysis
Date: 9-13 February 2015
Presenter: Associate Professor Demetris Christodoulou, Director of MEAFA research group
Description: This workshop focuses on exploratory data analysis methods for unveiling patterns from data, and suggestive relationships that would inform improved prospective modelling and updated expectations, including the detection of non-linearities, asymmetries, outliers and other data complexities. The workshop will extend to a discussion of nonparametric statistics and robust analysis methods, which are motivated from the need to deviate from rigid assumption-driven mathematical formulations that often fail to be confirmed by observables.
Title: Multilevel/Mixed models
Date: 10-14 February 2014
Presenter: Dr Yulia Marchenko, Director of Biostatistics, StataCorp LP.
Description: The workshops focuses on mixed models containing both fixed effects and random effects not directly estimated but instead summarized through the unique elements of their variance-covariance matrix. Mixed models may contain more than one level of nested random effects, and hence, these models are also referred to as multilevel or hierarchical models, particularly in the social sciences. The approach to linear mixed models is to assign random effects to independent panels where a hierarchy of nested panels can be defined for handling nested random effects.
Title: Structural equation modelling
Date: 24-28 June 2013
Presenter: Kristin MacDonald, Chief Statistician, StataCorp LP.
Description: The workshops focuses on developing an in-depth understanding of SEM approach to modelling causal relations with latent determinants. SEM is an alternative way of thinking, formulating and estimating simple and complex cause-and-effect models, from simple linear regressions and instrumental variable models to measurement models, systems of simultaneous equations, confirmatory factor analysis, correlated uniqueness models, latent growth models and more.
Title: Monte Carlo simulation
Date: 11-15 Februar 2013
Presenter: Associate Professor Demetris Christodoulou, Director of MEAFA research group
Description: The workshop focuses on Monte Carlo (MC) simulation describes the process of generating repeated random sampling for imitating real situations through the use of reasonable probabilistic assumptions. MC simulation is most appropriate for evaluating complex deterministic formulations that are characterised by significant uncertainty. The principles of MC simulation is demonstrated through a wide variety of applications from statistics, econometrics, business, and health.
Title: Advanced Time-Series methods
Date: 6-10 February 2012
Presenter: Dr David Drukker, Director of Econometrics, StataCorp LP.
Description: The workshop focuses on time-series analysis and and latest developments in time-series methods, including filters, unobserved components, structural VAR, and dynamic factor models. A particular emphasis is placed on analysing state-space models, which use state variables to describe a system by a set of first-order differential or difference equations, and decompose the time series into a number of distinct components.
Title: Survival analysis
Date: 18-22 July 2011
Presenter: Professor Rory Wolfe, Director of the Biostatistics Consulting Service, Monash University.
Description: The workshop focuses on mastering survival analysis is in decoding the jargon and in understanding the set of adjustments needed to be made when the data measures time to failure or some other event of interest, are more easily understood when compared directly to their non-survival analogs. The workshop covers non-parametric analysis, semi-parametric analysis and parametric methods of analysis.
Title: Data visualisation
Date: 15-18 February 2011
Presenter: Dr Bill Rising, Director of Educational Services, StataCorp LP
Description: The workshop focuses on providing an in depth analysis of graphing capabilities. Data visualisation examples are demonstrated for a variety of data structures, including cross-sectional data, time-series data, longitudinal data and survey categorical data. The aim is to learn how to produce informative, accurate, robust, complex and beautiful graphs using reproducible routines for multidimensional complex data.
Title: Multiple imputation
Date: 21-25 June 2010
Presenter: Dr Yulia Marchenko, Director of Biostatistics, StataCorp LP.
Description: The workshop provide presents multiple imputation (MI) analysis and a detail description of the three stages of MI (imputation, complete-data analysis, pooling) with applications in Stata 11. Various imputation techniques will be discussed with the main focus on multivariate normal imputation. A number of examples demonstrating how to safely and efficiently manage multiply-imputed data will be provided. Linear and logistic regression analysis of multiply-imputed data as well as several post-estimation features will be presented.
Title: Multilevel/Mixed Models
Date: 10-12 February 2010
Presenter: Dr Roberto G. Gutierrez., StataCorp Director of Statistics
Description: The workshop focuses on multilevel/mixed models contain both fixed effects analogous to the coefficients in standard regression models and random effects not directly estimated but instead summarized through the unique elements of their variance-covariance matrix. Mixed models may contain more than one level of nested random effects, and hence these models are also referred to as multilevel or hierarchical models, particularly in the social sciences.
Title: Survey data analysis
Date: 13-17 July 2009
Presenter: Professor Richard Gerlach, Chair of Business Analytics, University of Sydney Business School.
Description: The workshop introduces the concept and methods for survey data analysis and explains its distinction to the other types of quantitative analysis. It focuses on sampling methods and survey design, including multi-stage sampling, cluster sampling, mixed sampling approaches, design effects and variance components estimation. It uses the European Social Survey to apply the principles and concepts of empirical survey data analysis.
Our professional development workshops are aimed for the professional researcher and the quant-minded research student. The workshops cover theory and applications for the latest advances in data science and data analytics methods. The workshops are hands-on and are delivered by world recognised experts on the subject.
The PEMA workshop platform is modelled on the renowned workshops offered by the MEAFA research group for more than a decade. The workshops are widely recognised by the academia, private sector, state and federal governmental agencies for their high quality state-of-the-art content, as shown in the list of participant organisations just below.
The net proceeds from offering these workshops go to funding PEMA PhD scholarships and research development programs.