Confessions of a pragmatic statistician

Chris Chatfield
2002 Statistician (London. Print)  
The paper reflects on the author's experience and discusses how statistical theory, sound judgment and knowledge of the context can work together to best advantage when tackling the wide range of statistical problems that can arise in practice. The phrase 'pragmatic statistical inference' is introduced.  2002 Royal Statistical Society 0039-0526/02/51001 'activities of applied statisticians in the real world who are subject to constraints of finite resources, many problems to examine, and mixed
more » ... examine, and mixed expertise of consumers'. Tackling real life statistical problems This section briefly revisits some key aspects of problem solving. Good statistical practice (e.g. Deming (1965) , Preece (1987) and Chatfield (1995a)) is an essential prerequisite to any application of theory, and any competent statistician, whatever his or her philosophy, will start by asking questions, clarifying objectives, obtaining background information to tackle the problem 'in context', collecting 'good' relevant data, assessing the quality and structure of the data, deciding what to do about outliers and missing observations, and so on.
doi:10.1111/1467-9884.00294 fatcat:5qj2xsd6xjfgvjw3jqcfks6bgi