Event rate

from Wikipedia, the free encyclopedia
Racine carrée bleue.svg
 This item has been on the quality assurance side of the portal mathematics entered. This is done in order to bring the quality of the mathematics articles to an acceptable level .

Please help fix the shortcomings in this article and please join the discussion !  ( Enter article )

In the Epidemiology and Biostatistics which is event rate (engl .: "event rate" ) is the frequency with which an adverse event (eg. B. disease) within a certain period of time or a specified space occurs. The event rate is a term from probability theory that is mainly used in the fields of mathematics, science and medicine.

Application in medical statistics

In medical statistics (also: biostatistics ), the event rate describes the relative frequency with which a certain event (e.g. the occurrence of a symptom , an illness or an alleviation / healing ) is observed in a group of patients or test persons. To do this, one divides the number of observed events by the number of observed patients or test persons. For example, if 28 headaches occur in a group of 100 patients, the event rate is 0.28 or 28%.

To find out whether a medical treatment is effective, it is best to compare it to placebo , ideally in a double-blind study . You then count how often the event concerned occurs in the placebo group and relate this to the number of patients treated with placebo. We obtain the controlled event rate (ger .: "control event rate" - CER). This is compared with the experimental event rate (ger .: "experimental event rate" - EER), ie, the event rate in the group receiving medical treatment.

From the CE and the EER, the leave Absolute risk reduction (ARR), the relative risk reduction (RRR) and number needed to treat (ger .: "number needed to treat" - NNT) calculate a form of therapy that for the assessment of their effectiveness and economy are important. The significance of this data is largely determined by the associated confidence interval . If this is not stated in a publication, the statistical information must be assessed critically.

The patient-related experimental event rate (ger .: "patient's expected event rate" - PEER) refers to the number of events that you would expect in a patient who is neither therapy nor receive placebo, so to speak, the "natural" risk that a Event, e.g. B. headache occurs.

Please note: With the above Event rates are just a statistical description of events in observed groups of patients or test subjects. In this way, nothing can be said about the causal relationship between treatment and non-occurrence of an event. In order to find out with what probability the difference between CER and EER is really due to the treatment or is simply a random effect , i.e. whether the result is statistically significant with a high probability , one must use statistical tests .

See also

literature

  • Werner Timischl: Biostatistics. An introduction for biologists and medical professionals. Vienna 2000, ISBN 3-211-83317-X .
  • Harvey Motulsky: Intuitive Biostatistics. Oxford 1995, ISBN 0-19-508607-4 .

Web links