Glossary

Absolute risk reduction (ARR): The difference between the rate of an event (outcome) in one treatment group compared to the rate of an event in another treatment group

Abstract: A summary of a study

Activity: An International Classification of Functioning, Disability and Health (ICF) term that describes actions such as walking, climbing stairs, or getting out of bed

AGREE II: A published, open-access tool for the appraisal of clinical practice guidelines; the product of the AGREE Collaboration (https://www.agreetrust.org), an international collaboration of researchers and policy makers

Allocation concealment: Technique that refers to researchers being sufficiently blinded to the sequence in which participants would be randomized into groups

Alpha level: The agreed-upon value for the probability of chance in explaining the results of a study; it is typically 5% (0.05)

Analysis of covariance (ANCOVA): A parametric statistic used to compare means and to remove the contribution of a factor that is present during treatment that was not controlled in the experimental design

Analysis of variance (ANOVA): A parametric statistic used to compare results for more than two groups

Applicability: The relevance of a sample or study to your patient or patient group

Appraisal: The process of determining whether a research article is applicable to a research question and whether it is of sufficient quality to help guide clinical decision-making

Assessment of clinical heterogeneity: An analysis of the similarities of the study populations, interventions, and outcome measures among the studies included in a meta-analysis

Autocorrelation: Positive correlation among data points from the same subject

Background questions: Questions that supply general information and are not specific to an individual patient

Basic science research: Often involves non-human research and is fundamental to evidence based physical therapy; typically tests theory

Beta-weight: A standardized value that gives a weight (amount of contribution) to each of the independent variables in a regression equation

Bias: Occurs when a study’s results are affected by unknown or unacknowledged errors resulting from the study’s design or protocols

Blinding: Appropriate steps taken to mask study participants and study personnel to each participant’s group assignment

Body functions and structures: An International Classification of Functioning, Disability and Health (ICF) term that describes variables at the level of bodily functions and specific structures (impairments)

Bonferroni correction: A planned statistical test used to correct for conducting multiple statistical tests and the possibility of a type I error

C statistic: A statistic to determine the probability of chance; used with small data sets or data with serial dependency

Case control studies: Studies conducted after an outcome of interest has occurred. The factors that contributed to the outcome are studied in a group ...