Cynefin, Statistics and Decision Analysis Simon French Manchester Business School University of Manchester Manchester, M15 6PB
[email protected] April 2011 Abstract David Snowden‟s Cynefin framework, introduced to articulate discussions of sense-making, knowledge management and organisational learning, also has much to offer discussion of statistical inference and decision analysis. In this paper, I explore its value particularly in its ability to help recognise which analytic and modelling methodologies are most likely to offer appropriate support in a given context. I also use the framework to offer a further perspective on the relationship between scenario thinking and decision analysis in supporting decision makers. Keywords: Cynefin; Bayesian statistics; decision analysis; decision support systems; knowledge management; scenarios; scientific induction; sense-making; statistical inference. 1 Introduction Several years back David Snowden visited Manchester Business School and gave a seminar on knowledge management. At this he described his conceptual framework, Cynefin, which, among other things, offers a categorisation of decision contexts (Snowden 2002). At first I thought this said little if anything more than many other ways of categorising decisions, such as the strategy pyramid stemming from Simon (1960) and beyond Simon back to the prehistory of military theory: viz. strategic, tactical and operational (see Figure 2 below). However, a colleague, Carmen Niculae, had more insight and working with her and others, I have since come to realise Cynefin‟s power to articulate discussions of inference and decision making. In the following, I want to explore the ideas underlying Cynefin and their import for thinking about statistics and decision analysis. There is nothing dramatic in anything I shall say.