Accounting for measurement error: a critical but often overlooked process

Abstract

Because of instrument imprecisions and human inconsistencies, measurements are not free of error. Technical error of measurement (TEM) is the variability encountered among dimensions when the same specimens are measured at multiple sessions. A goal of a data collection regimen is to minimize TEM. The few studies that actually quantify TEM— regardless of discipline—report that it is substantial and can affect results and inferences. Objective: This paper reviews some statistical approaches for identifying and controlling TEM. Statistically, TEM is part of the residual (―unexplained‖) variance in a statistical test, so accounting for TEM—which requires repeated measurements—enhances the chances of finding a statistically significant difference if one exists. Methods: It has been the author’s intention to perform a thorough review and discuss statistical design relating to types of error and statistical approaches to error accountability. This paper address’ issues of landmark location, validity, technical and systematic error, ANOVA, scaled measures and correlation coefficients in order to guide the reader towards correctly identify true experimental differences. Conclusions: Researchers commonly infer characteristics about populations from comparatively restricted study samples. Most inferences are statistical, and, aside from concerns about adequately accounting for known sources of variation with the research design, an important source of variability is measurement error. Variability in locating landmarks that define variables is obvious in odontometrics, cephalometrics and anthropometry, but 4 the same concerns about measurement accuracy and precision extend to all disciplines. With increasing accessibility to computer-assisted methods of data collection, the ease of incorporating repeated measures into statistical designs has improved. Accounting for this technical source of variation increases the chance of finding biologically true differences when they exist.