Topic: Statistics and analysis
A factor that can be controlled, changed or measured in a study.
The number of participants or study objects (e.g. tissue samples) involved in a study, e.g. within a clinical trial. A larger sample size provides stronger evidence, as it as associated with greater statistical power (see power calculation).
Describes a mathematical measure to determine if an observed effect is likely based on chance alone or not. A difference is said to be statistically significant if it is greater than what might be expected to happen by chance alone. See p-value.
How well a measurement measures what it should.
A type of calculation which works out the sample size required to detect a real (significant) difference between groups that are compared (e.g. treatment vs control) with a certain probability.
The chance of something happening (see risk).
A statistical term. the median is the middle value in a set of numbers when they are arranged in order from smallest to largest (or largest to smallest). It separates the higher half from the lower half of the data. For example, in the following dataset: 2, 4, 6, 8, 10. The median value is […]
A statistical term. It helps show whether a difference found between groups that are being compared is due to chance (see statistically significant). A small p-value (typically less than 0.05, shown as p<0.05) usually means that the difference between groups is not due to chance alone, but is due to some other factor, such as […]
A false negative is a test result that incorrectly shows a condition is not present, when it actually is. For example, a blood test might suggest that a person does not have cancer, but when other confirmatory tests are performed (e.g. biopsy) it turns out that the person does have cancer and the blood test […]
A false positive is a test result that incorrectly shows a condition is present, when it actually is not. For example, a blood test might pick up something unusual and suggest that a person has cancer, but when other confirmatory tests are performed (e.g. biopsy) it turns out the person does not have cancer and […]