Evidence-based Research Methods for Chinese Medicine by Siu-wai Leung & Hao Hu

Author:Siu-wai Leung & Hao Hu
Language: eng
Format: epub
Publisher: Springer Singapore, Singapore

7.5 Sample Size of Raters

The major factor that influences the power of statistical analysis in reliability studies is the number of cases being analyzed by each rater. It is not advantageous to increase too much, the number of raters because the effects on the statistical power and amplitude of confidence intervals are small. It was demonstrated that the number of raters is inversely proportional to the required number of cases, although the saving in sample size rapidly decreases after five raters [36]. Although interrater reliability might be evaluated for two raters only, a minimum sample size of five raters is easily obtained and strongly advised.

It is worth noting that estimates of sample sizes for raters are related to each group being analyzed in the research. This means that if a study protocol aims to compare the reliability between two groups of raters defined by a given factor—say, <5 and ≥5 years of clinical practice—each group must present the minimal sample size of raters as estimated.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.