Disclosure‐protected Inference Using Generalised Linear Models

Vast amounts of data that could be used in the development and evaluation of policy for the benefit of society are collected by statistical agencies. It is therefore no surprise that there is very strong demand from analysts, within business, government, universities and other organisations, to access such data. When allowing access to micro‐data, a statistical agency is obliged, often legally, to ensure that it is unlikely to result in the disclosure of information about a particular person or organisation. Managing the risk of disclosure is referred to as statistical disclosure control (SDC). This paper describes an approach to SDC for output from analysis using generalised linear models, including estimates of regression parameters and their variances, diagnostic statistics and plots. The Australian Bureau of Statistics has implemented the approach in a remote analysis system, which returns analysis output from remotely submitted queries. A framework for measuring disclosure risk associated with a remote server is proposed. The disclosure risk and utility of approach are measured in two real‐life case studies and in simulation.     

EFFECTS OF SECTOR AGGREGATION ON CO2 MULTIPLIERS IN MULTIREGIONAL INPUT–OUTPUT ANALYSES

The past few years have seen the emergence of several global multiregional input–output (MRIO) databases. Due to the cost and complexity of developing such extensive tables, industry sectors are generally represented at a rather aggregate level. Currently, one of the most important applications of input–output analysis is environmental assessments, for which highly aggregate sectors may not be sufficient to yield accurate results. We experiment with four of the most important global MRIO systems available, analyzing the sensitivity of a set of aggregate CO₂ multipliers to aggregations in the MRIO tables used to calculate them. Across databases, we find (a) significant sensitivity to background system detail and (b) that sub-sectors contained within the same aggregate MRIO sector may exhibit highly different carbon multipliers. We conclude that the additional information provided by the extra sector detail may warrant the additional costs of compilation, due to the heterogeneous nature of economic sectors in terms of their environmental characteristics.     

Heuristic learning and the discovery of specialization and exchange

I develop and calibrate an agent-based model of boundedly rational, adaptive agents in a two-good production and exchange economy to replicate human-subject outcomes in the same eight-person experimental economy. To test agents’ ability to capture human behavior, I extend the model and use its output to make predictions about a second experimental environment in which the group of eight agents is slowly constructed by merging smaller groups. This environment improves human-subject performance in the specialization and exchange task, and commensurate improvement emerges for some parameterizations of the agent-based model. This iterative process yields incremental improvement of decision-level theories about economic discovery.     

Are we operating effectively? A lean analysis of operating theatre changeovers

Hospital operating theatres are a critical but costly resource in healthcare processes. Their efficiency and utilisation impact upon hospital finances, clinical effectiveness and patient outcomes. Operations management techniques have now been applied widely to optimise flow. An important challenge is to balance the needs of process flexibility, efficiency and work standardisation with clinical requirements. This paper applies operations management methods to analyse elective orthopaedic surgery at five international hospitals to describe the issues that affect operating theatre productivity. It utilises an innovative method of video analysis to observe patient changeovers over 29 days of surgery and data is analysed to understand the causes of variability and waste. The findings suggest that processes which are standardised via operations management methodologies can improve productivity in a process that exhibits wide variation in practice. There are apparent trade-offs associated with efficiency and clinical concerns such infection control, that lead to different standard process archetypes being utilised. Recommendations for standardising patient changeovers are provided.     

The M/M\1 queue in a heavy-tailed random environment

We consider an M / M /1 queue with the special feature that the speed of the server alternates between two constant values s_L and s_H > s_L . The high-speed periods are exponentially distributed, and the low-speed periods have a regularly varying distribution. We obtain explicit asymptotics for the tail of the workload distribution. The two cases in which the offered traffic load is smaller respectively larger than the low service speed are shown to result in completely different asymptotics.     

External communication behaviour of purchasers—effects on supplier management performance

This article presents findings of a research effort that focuses on the relationships among the external communication behaviour of purchasers, individual and contextual factors and the performance in supplier management. Communication quantity, openness and friendliness were identified as dimensions of individual communication behaviour. Information and relationship quality were used as the two dimensions of communication quality. The results, based on structural equation analysis, provide support for the positive influence of individual communication behaviour on communication quality and supplier management performance. Results suggest that relationship quality appears to be of great significance in the model. Oral communication capability and purchasers’ attitudes towards individual communication with suppliers also play important roles in explaining external communication behaviour of purchasers.     

Discretionary fiscal policy and economic activity in Greece

This paper investigates the effects of discretionary fiscal policy changes on economic activity and its subcomponents in Greece in the period 2000–2011. Changes in government spending and net taxes have Keynesian effects. An increase in government consumption has the most pronounced positive effects on output growth, private consumption and non-residential investment, while it reduces residential investment. Cuts in the public investment programme crowd in private investment, but are associated negatively with the net exports ratio. Both indirect and direct tax hikes lower private consumption, private investment and output growth. However, higher direct taxes by lowering disposable income they reduce import demand, thus, improving the trade balance.     

Flexibility at different stages in the life cycle of projects: An empirical illustration of the “freedom to maneuver”

Many textbooks on project management present illustrations concerning the relative size of project attributes during different project phases. The derived models all have attributes in common, such as uncertainty, significance of decisions, and degree of freedom to maneuver, that are typically high in the beginning of the project and low in the end. At the same time, variables such as the accumulated cost and available information begin at low levels and end up at a high level at the end of the project. Based on empirical data from projects, this paper illustrates and quantifies one of these attributes, the freedom to maneuver, in different project phases.     

A Common Base Answer to the Question “Which Country Is Most Redistributive?”*

We believe that what most authors have in mind when referring to the “most redistributive country” is a tax and transfer schedule that is most redistributive across all pre-tax and transfer income distributions. In order to measure each country's tax and transfer redistribution according to the same baseline, we suggest using the transplant-and-compare method of Dardanoni and Lambert (2002, Journal of Public Economics 86, 99–122) to establish a common base. The redistributive effects of countries’ tax and transfer schedules are illustrated by employing microdata on eight countries from the Luxembourg Income Study (LIS). Of these eight countries, Finland is found to be the most redistributive country, according to the common base method.