See correlation

a belief, claim or hypothesis that is accepted as true (or as certain to happen), without evidence.

See 'cognitive bias' or 'methodological bias'

systematic pattern of deviation from rational or logical judgment based on inherent and unconscious psychological processes. Well known examples are confirmation bias, availability bias, group conformity, and authority bias.

A study in which a group (sometimes referred to as an “intervention,” “treatment” or “experimental” group) that is exposed to an intervention expected to have an effect (the assumed cause), which is then compared with another group (known as the “control” or “comparison” group) that is not.

Provides the upper and lower boundaries between which we expect – usually with a 95 percent certainty – the true value of a point estimate (mean, percentage, or effect size) to fall. Used to determine the precision of an effect size.

a third variable that distorts (confounds) the relationship between two other variables.

the degree or strength of a (linear) relationship between two variables. The relationship may be positive (an increase in one variable is associated with an increase in the other) or negative (an increase in one variable is associated with a decrease in the other). The square of correlation indicates how much variation in one variable is explained by the other.

process of systematically judging the quality or trustworthiness of evidence.

a quantitative measure of the strength of a relationship, or the degree of difference between two groups, controlling for the bias that sample size introduces.

the organizational outcome of an intervention

An intervention is effective if it causes something to happen that is wanted.

making decisions (e.g. about claims) through the conscientious, explicit use of critically appraised evidence from multiple sources

information supporting (or contradicting) a claim, assumption or hypothesis

A fair comparison of interventions is one where the only important difference between the groups that are compared is the intervention they receive. See also comparison of interventions

In a comparison of interventions, fair means not giving an advantage to one treatment over another.

extent to which the evidence also applies to other populations or organizations.

indicator of the probability that an outcome will occur.

study that involves repeated observations (measurements) of the same variable(s) over a certain period of time (sometimes even years).

the difference between a measured value and its true value.

a statistical approach combining the results from multiple studies in order to obtain a trustworthy estimate of effect sizes and to resolve uncertainty when studies find different results.

systematic pattern of errors or deviations from population values or true scores; these errors are introduced by some feature(s) in the research design. For example, methodological bias can occur when a certain kind of answer is encouraged and another kind of answer discouraged, for example, social desirability bias can lead individuals to agree with positively worded questions and disagree with negatively worded questions regardless of the actual content of the questions.

In intervention comparisons, an outcome (or ‘outcome measure’) is something good or bad that can happen as a result of an intervention

articles submitted to peer reviewed journals are first evaluated and critiqued by independent, anonymous scientists in the same field (peers) to determine whether they merit publication in a scientific journal.

the extent to which an event or outcome is likely to occur, measured by the ratio of the favorable cases to the whole number of cases possible.

The experience and judgment of managers, consultants, business leaders and other practitioners - differs from intuition and personal opinion because it reflects the specialized knowledge acquired by the repeated experience and practice of specialized activities

the degree to which the results of a measurement can be depended upon to be accurate. Related to the consistency or repeatability of measurement results.

indication of how well the data obtained from a sample accurately represents the entire population. The more representative the sample, the more confident we can be that we can generalize the evidence to the whole population. See also generalizability, a related but different term.

scientific studies published in peer-reviewed academic (scholarly) journals

A side effect is a harmful or unpleasant effect of an intervention that is not planned.

people (individuals or groups) whose interests affect or are affected by an organization’s decision and its outcomes.

Statistical metric that is often explained as "unlikely to have happened by chance". Unfortunately this interpretation is not accurate. You may be surprised, because this is probably what you learned in class or read in textbooks. So, what does ‘statistically significant’ mean? Unfortunately, it is very hard to explain what it really means. The official definition looks like this: “The probability of getting results equal or even more extreme as the ones you observed, if the null hypothesis would be true.” In other words, it is the probability of your data, given your hypothesis. Still confused? Don’t worry about it. As you can see in this video, not even scientists can easily explain what statistically significant (also referred to as a p-value) really means.

A summary of studies addressing a clear question, using systematic and explicit methods to identify, select, and critically appraise relevant studies, and to collect and analyse data from them

deserving of trust or confidence, used in evidence-based decision making to refer to the extent to which evidence is reliable and valid.

An unfair comparison of interventions is one where there are important differences between the groups that are compared besides the treatments they receive.

the extent to which a concept, measurement or result is consistent with the real world.