Review article
https://doi.org/10.21860/medflum2017_187369
Random errors in research and the importance of sample size
Goran Poropat
; Zavod za gastroenterologiju, Klinika za internu medicinu, Klinički bolnički centar Rijeka, Rijeka, Hrvatska
Sandra Milić
; Zavod za gastroenterologiju, Klinika za internu medicinu, Klinički bolnički centar Rijeka, Rijeka, Hrvatska
Abstract
Random errors are essential parts of every experiment and clinical research resulting from sampling variability. Research results should be applicable to the entire population, which is why the representativeness and adequate sample size are of crucial importance. By conducting a specific measurement on a population sample, we try to determine the probability of the observed difference between measured variables being the result of chance or acutal difference in the population. This probability is known as the P-value. Chance in research manifest itself as error type I and error type II. The risk of random error diminishes by increasing the number of measurements or enlarging the sample size. Therefore, it is necessary to calculate and define the required sample size based on a priorly defined primary outcome. This enables the implementation of credible and methodologically strong research resulting in solid evidence.
Keywords
random errors; sample size; error type I and II; P-value
Hrčak ID:
187369
URI
Publication date:
1.12.2017.
Visits: 7.697 *