Methodological advisor(Redirected from Statistical consultant)
A methodological advisor or consultant provides methodological and statistical advice and guidance to clients interested in making decisions regarding the design of studies, the collection and analysis of data, and the presentation and dissemination of research findings. Trained in both methods and statistics and communication skills, advisors may work in academia, industry, or the public sector.
Education and employmentEdit
Methodological advisors generally have post-graduate training in statistics, as well as relevant practical experience. In addition, advisors may also have significant education and experience in the particular field they work in. Some universities offer specific graduate programmes in fields such as biostatistics, psychological methods, or methodology and statistics for the medical, behavioural, and social sciences.
Methodological consultants primarily find work in academia and industry. In the private sector, consultants may be part of an organisation, employed by a consultancy firm, or self-employed. Many universities offer in-house methodological advice for researchers, as well as, in some cases, services for outside clients. The advisors may also be researchers of their own right and be deeply involved with particular projects. Project statisticians, in particular, are embedded with research groups and often developed a deep understanding not just of statistics, but also of the research topics themselves. In contrast, independent advisors are often only consulted on specific questions, and may be less involved with the project as a whole.
Disciplines in which methodological advice is sought stretch the entire width of the quantitative sciences, but may in particular include the medical sciences, biology, psychological research, and business studies. Advisors are also consulted in public administration, where they may be involved at all levels of governance. In the legal system, consultants may be called upon as expert witnesses, in particular in cases that involve statistical considerations.
Range of tasksEdit
The role of a methodological advisors varies from project to project, but can include any point in the research cycle. While cross-sectional consulting may only occur at one point during a project, longitudinal consulting may mean that the advisor stays with the project from beginning to end. Hence, advice is not limited to statistical questions. Broadly speaking, questions may concern the design of studies, choice or construction of measurement instruments, analysis of data, and presentation of results. In particular, common questions include:
- design of experiments and research studies
- plotting data
- measurement instruments (choosing, constructing & analysing)
- determination of adequate sample size to detect a hypothesised effect
- determination of an adequate sampling procedure for a study, survey or experiment
- supervision of data collection to ensure elements of the population are being sampled correctly
- statistical analyses (e.g., analysis of variance, regression, etc.) of data to address research hypotheses
- the write-up of statistical results for grant proposals, manuscripts, professional conferences, or other presentations.
Giving methodological advice can mean answering specific questions or performing mundane data analyses, but may often go beyond that. In particular when clients have little understanding of research methods and statistics, consultants may have to clarify substantive questions and to translate them into methodological and statistical procedures. In private companies, the form of consultancy does not necessarily depend on the understanding of the client. Different companies may offer different forms of consulting, ranging from providing a quick fix for specific problems, provide extensive explanations to the client or even running the whole analyses.
In some cases, this may also entail profound ethical considerations. The client's occupation may form a constraint for the form in which consultancy can be offered. For example, running data-analyses for companies may not be a problem, where doing this for a bachelors or masters student can be considered fraud.
Although statisticians were traditionally trained largely on a technical skill set, recent times have brought a realisation that advisors need to be proficient in communication, teamwork, and problem-solving skills just as well as in methodological questions. As such, they have to be able to elicit explanations from clients and to give clear explanations of methods and statistics themselves. Because in some cases the implications of methodological advice may be profound (e.g., it may not be possible to conduct certain experiments, or to gain certain insights from data already collected), consultants also have to be able to communicate such ramifications.
- Boen, J. R., & Zahn, D. A. (1982). Human Side of Statistical Consulting. Wadsworth Publishing Company.
- Cabrera, J., McDougall, A. (2002). Statistical Consulting. Springer.
- Derr, J. (1999). Statistical Consulting: A Guide to Effective Communication. Duxbury Press.
- Hand, D. J., & Everitt, B.S. (1987). The Statistical Consultant in Action. Cambridge University Press.
- Adèr, H.J., Mellenbergh, G.J., & Hand, D.J. (2007). Advising on research methods: A consultant’s companion. Johannes van Kessel Publishing: Huizen, The Netherlands.
- Adèr, H.J., Mellenbergh, G.J., & Hand, D.J. (2008). Advising on research methods: A consultant’s companion. Johannes van Kessel Publishing: Huizen, The Netherlands.
- Van Belle, G. (2008). Statistical rules of thumb (2nd ed.). New York, NY: Wiley.
- Derr, J. (2008). Having an impact in a multi-disciplinary setting. In H. J. Adèr & G. J. Mellenbergh (Eds.), Proceedings of the 2007 KNAW colloquium Advising on research methods (pp. 11-20).