Face validity: When an instrument appears to measure what it is intended to measure.1 See also validity.

Failsafe N: A calculation used to account for publication bias that estimates the number of unpublished or unretrieved nonsignificant studies that would nullify or lower the significance in a meta-analysis.31 Also called file-drawer analysis.

False negative (FN): A test result that is negative for a person who has the disease.4

False positive (FP): A test result that is positive for a person who does not have the disease.4

Fixed-effect model: A model used in meta-analysis to calculate a pooled effect estimate using the assumption that all factors that could influence the effect size are the same in all the studies, and therefore the true effect size is the same (fixed) in all studies.32 Since all studies share the same true effect, it follows that that observed effect size varies from one study to the next only because of the random error inherent in each study. An alternative model is the random-effects model.

Forest plot: A graphical representation of the individual results of studies included in a meta-analysis together with the combined meta-analysis result.6 The plot also allows readers to see the heterogeneity among the results of the studies.

Functional status: A measure of a person’s ability to perform his or her daily activities, often called activities of daily living (ADL).4