Some statistical directions for the evaluation of the method error when measuring a quantitative variable

Ary José Dias MENDES, Ary dos SANTOS-PINTO

Introduction: the method error must be quantified to support the validity of the research and its clinical application. The determination of the reliability of the landmark identification to obtain measurements constitutes a fundamental precondition for a correct interpretation and utilization of the data. Each observed measurement can be analyzed through its actual value and its error component. The reliability is verified through repeated measurements. Aim: the purpose of this paper was to describe a statistical method which allows the researcher to verify if the measurements which he obtained at a certain moment are repeated by him at a posterior moment. This method confirms the non occurrence of the systematic error and allows an evaluation of the occurrence of the casual error, always presents in any form of measurement. Also, it presents the application of this statistical method in data referring to two cephalometric measurements and shows the syntax for the resolution of the method error through the use of the SPSS software for computers.

Keywords: Method error. Statistics. Cephalometry. Reliability.

Saturday, November 23, 2024 09:56