Statistics: A Life Cycle View

Abstract

ABSTRACTStatistics has gained a reputation as being focused only on mathematical modeling, data collection, and data analysis. This article is about an expanded view of the role of statistics in research, business, industry, and service organizations. Such an approach provides an antidote to the narrow view of statistics outlined above in an effort to reposition it as the leading profession in the analytics domain. This view creates a need for focused research activities and the development of new methods and tools, often in collaboration of statisticians with experts in other disciplines (Kenett 2012). Specifically we discus here a “life cycle view” consisting of (1) problem elicitation, (2) goal formulation, (3) data collection, (4) data analysis, (5) formulation of findings, (6) operationalization of findings, (7) communication, and (8) impact assessment. These eight phases, with internal iterations, combine the inductive–deductive learning process studied by George Box (1997). Covering these phases, beyond the data analysis phase, increases the impact of statistical analysis and enhances the level of generated knowledge and information quality. The envisaged overall approach presented here is that the research and practice of applied statistics needs to involve a trilogy combining (1) a life cycle view, (2) an analysis of impact, and (3) an assessment of the quality of the generated information and knowledge. We begin with a section introducing the problem, continue with a review of the information quality (InfoQ) concept presented in Kenett and Shmueli (2014), and proceed with a description of the eight life cycle phases listed above. Adopting a life cycle view of statistics has obvious implications to research, education, and statistical practice. These are presented in the context of several examples. We conclude with a discussion of such implications.