Measurement error: What is it? Does it matter? What to do about it?
John P. Buonaccorsi
Professor Emeritus, Department of Mathematics and Statistics
University of Massachusetts-Amherst
Frequently variables that enter into a statistical analysis are not able to be observed exactly. Examples include dietary intake or physical activity over a certain period of time, population abundance, disease rate, chemical or biological properties of water or soil samples, genetic quantities including methylation rate, expenditure or income, disease status (and many other variables with a yes/no status), etc. The “measurement error” or as it is known for a qualitative variable, misclassification, can arise for a variety of reason including instrument error, sampling error (often from sampling over time and/or space), recall bias and a variety of other reasons. In this talk I will give a (non-technical) overview of the nature of measurement errors, what happens if you ignore it in a variety of problems, including estimating means and proportions, contingency table analysis and regression analysis, and what strategies are available to correct for measurement error. Examples will be presented from a variety of disciplines.
John Buonaccorsi is Professor Emeritus of Mathematics and Statistics at the University of Massachusetts-Amherst. He received his B.A. from Providence College in 1975, his M.S. and Ph.D. degrees from Colorado State University and has been at the University of Massachusetts since 1982. He was a long-time member of the University’s Statistical Consulting Center and coordinator of the graduate options in Statistics for many years. He is the author of over 70 articles and book chapters and is author of the 2010 book “Measurement Error: Models, Methods and Applications”, part of the Chapman-Hall series on interdisciplinary statistics. His original research interests were in optimal experimental design, estimation of ratios and calibration, followed by a focus on measurement error, an area he has worked in for over 25 years. He has also published extensively in various applied areas including quantitative ecology, with a recent emphasis on population dynamics. He has a long-standing collaboration with colleagues at the University of Oslo Medical School addressing measurement error methods in epidemiologic contexts.
