Glossary

Stability is the ability of a substance to remain unchanged. Changes may occur due to the environment that the substance is in, e.g. being exposed to sunlight or water, or being in the body. Changes may also occur due to chemical and biological processes found inside the substance.

The standard deviation is a measure of the amount of variation within a data set. If all values in a data set are very close together, the standard deviation will be close to zero. In such cases, the data points will all lie close to the mean (average). A high standard deviation indicates that the values are much more spread out.

The standard deviation is normally included when clinical trial results are reported because it provides a (rough) guide to statistical significance. Take, for example, a clinical trial in which the observed symptom reduction is greater than one would expect if the medicine had no effect. The difference (between the observed result and what one would expect if the medicine had no effect) would generally have to be greater than two times the standard deviation to be regarded as statistically significant.

Standard Operating Procedure

Standardised Mortality Ratio

A statistical analysis plan (SAP) describes the planned analysis for a clinical trial. It contains the necessary details so that is can be followed and reproduced, providing clear and complete templates for each analysis.

Statistical inference is the process of drawing conclusions about a population through statistical analysis from a sample of that population.

For example: In clinical trials, hypothesis testing is a means of drawing conclusions on the effect of the medicines under study on the population that the sample of trial participants was drawn from. For instance, the null hypothesis would state that the medicine being studied does not affect symptom reduction while the alternate hypothesis would state the opposite. Statistical inference from the trial data will allow researchers to reject the null hypothesis if the analysis indicates a statistically significant effect.

Statistical significance is a fundamental aspect of hypothesis testing. In any experiment using a sample from a population (for instance, a sample of patients with a particular disease) there is the possibility that an observed effect may be due to differences between the sample and the whole population (sampling error) rather than the medicine under study. A test result is called statistically significant if it has been predicted as unlikely to have occurred by sampling error alone, according to a threshold probability: the significance level.

Statistical significance does not imply importance or practical significance. For example, the term clinical significance refers to the practical importance of a treatment effect. Researchers focusing solely on whether their results are statistically significant might report findings that are not relevant in practice. It is always prudent to report an effect size along with p-values. An effect size measure quantifies the strength of an effect, and makes it easier to draw conclusions on the practical implications.

Statistics are a mathematical methods of describing and drawing conclusions from data. Statistics are an essential part of the medicines development process at multiple stages.

Czech National Competent Authority. http://www.sukl.cz/"

Slovakian National Competent Authority. http://www.sukl.sk/"