Glossary
A
- Absolute Risk Difference
The difference in the number of events (outcome) between intervention and control groups (obtained by subtracting number of events in the intervention group from the number of events in the control group); usually reported as a %. Also see: Absolute risk reduction.
Cullum, N., Ciliska, D., Haynes, R.B., & Marks, S. (2008). Evidence-based nursing: an introduction. Oxford: Blackwell.
- Absolute Risk Reduction (ARR)
The difference in the number of events (outcome) in the control group minus the number of events (outcome) in the treatment group. For example, if the number of events (e.g. death) in the control group (not receiving the intervention) is 40 per 100 patients, while the number of events in the intervention group is 30 per 100 patients, ARR = 0.40 – 0.30; ARR = 0.10 or 10%.This means the intervention group has a 10% absolute lower risk of death than the control group.
Barratt, A., Wyer, P.C., Hatala, R., McGinn, T., Dans, A.L., Keitz, S., Moyer, V., Guyatt, G. (2004). Tips for learners of evidence-based medicine: 1. Relative risk reduction, absolute risk reduction and number needed to treat. CMAJ, 171(4), 353-358.
Centre for Evidence-Based Medicine, University of Oxford. (2005). Critical appraisal for therapy articles. Retrieved from http://www.cebm.net/index.aspx?o=1097
- Allocation
Process by which participants are assigned to either the experimental (intervention) group or comparison/control group in a study. Random allocation is done by chance. Studies that allocate participants that do not use random allocation usually do so by having participants selected themselves or are selected by the researcher to receive the intervention.
Cullum, N., Ciliska, D., Haynes, R.B., & Marks, S. (2008). Evidence-Based Nursing. An Introduction. Oxford: Blackwell.
- Analytic Study
A study that explores the relationship between one or more factors on an outcome:
- the effect of an intervention;
- exposure.
To quantify the relationship, the rate of the outcome in the intervention/exposed and control/comparison groups are compared. An experimental study implies active involvement of the researcher, (ie. Researcher involved in allocating participants to groups) while an observational study implies passive involvement of researcher (e.g. participants self-select to receive an intervention).
Glasziou, P., & Heneghan, C. (2009) A spotter’s guide to study design. Evidence Based Nursing, 12(3). P 71-72
- Appraise
The process of assessing the quality of study methods in order to determine if findings are trustworthy, meaningful and relevant to your situation.
National Collaborating Centre for Methods and Tools. http://www.nccmt.ca/eiph/appraise-eng.html