All Data are Wrong,but Some are Useful? Advocating the Need for Data Auditing

In a recent article from the Annals of Applied Statistics, Cox discussed the main phases of applied statistical research ranging from clarifying study objectives to final data analysis and interpreting results. As an incidental remark to these main phases, we advocate that beyond cleaning and preprocessing the data, it is a good practice to audit the data to determine if they can be trusted at all. A case study based on Ghanaian Official Fishery Statistics is used to illustrate this need, with Benford's law being the tool used to carrying out the data audit. Supplementary materials for this article are available online.     

Climate change and population migration in Brazil’s Northeast: scenarios for 2025–2050

This research contributes to an understanding of the relationship between climate change, economic impacts and migration. We model the long-term relationship (up to 45 years of projection) between demographic dynamics—particularly migration—driven by changes in the performance of the economy due to climate changes in the Northeast region of Brazil. The region is of particular relevance to the study of climate change impacts given its large human population (28% of Brazil’s population) and high levels of impoverishment, having an extensive semi-dry area which will be severely impacted by growing temperatures. Ultimately, the integrated model generates state- and municipal-level migration scenarios based on climate change impacts on the primary economic sectors and their articulations with other sectors. Results suggest that the predicted climate changes will impact severely the agriculture sector in the region, acting as a potential migration push factor to other regions in the country. Finally, we discuss how the increased vulnerability of some groups, particularly migrants, can be factored into Brazilian public policy and planning.     

100 key research questions for the post‐2015 development agenda

The Sustainable Development Goals (SDGs) herald a new phase for international development. This article presents the results of a consultative exercise to collaboratively identify 100 research questions of critical importance for the post‐2015 international development agenda. The final shortlist is grouped into nine thematic areas and was selected by 21 representatives of international and non‐governmental organisations and consultancies, and 14 academics with diverse disciplinary expertise from an initial pool of 704 questions submitted by 110 organisations based in 34 countries. The shortlist includes questions addressing long‐standing problems, new challenges and broader issues related to development policies, practices and institutions. Collectively, these questions are relevant for future development‐related research priorities of governmental and non‐governmental organisations worldwide and could act as focal points for transdisciplinary research collaborations.     

An application of catastrophe theory to management science process

Practicing management scientists often complain of the alleged irrational behavior on the part of the managers they are trying to serve, particularly when a manager suddenly and unexpectedly shifts behavior from one of support to one of resistance. The authors feel such behavior is only believed to be irrational because the management scientist is using the wrong mental model when projecting past behavioral patterns into the future. This paper attempts to solve this problem by using the newly developed catastrophe theory to develop a different model where sudden shifts in behavior are considered perfectly rational and explainable. The basic implication that is drawn from this new model is that successful implementation of management science depends on a sequence of interactions with the ultimate model user and that care in the structuring of these interactions can greatly enhance the probability of eventual user acceptance.     

Econometric analysis and managerial decision making

Econometric analysis is concerned with the quantitative relationships between economic variables and it can provide an important input into the decision making process of managers. Typically econometrics differs from other apsects of management science in that it considers problems primarily, though not exclusively, from a background of economics rather than of other disciplines and behaviour is usually dealt with at higher levels of data aggregation than the individual firm.This paper considers some applications of typical econometrics to the general area of managerial decision making, where primarily the techniques have a role to play in assisting the general process of data analysis. Initially discussion is pointed towards the use of the analysis for predictive purposes and the contrast with time series methods. Subsequently examples are presented where the objective is to obtain a better understanding of individual economic relationships that aim to be important inputs into the decision making process, for example cost and revenue analysis. Finally, an example is given of how these ideas contribute more generally to the activity of model building for the firm as a whole both for the purpose of forecasting and policy simulation.