Classification, Detection and Consequences of Data Error: Evidence from the Human Development Index
We measure and examine data error in health, education and income statistics used to construct the Human Development Index. We identify three sources of data error which are due to (i) data updating, (ii) formula revisions and (iii) thresholds to classify a country's development status. We propose a simple statistical framework to calculate country specific measures of data uncertainty and investigate how data error biases rank assignments. We find that up to 34% of countries are misclassified and, by replicating prior studies, we show that key estimated parameters vary by up to 100% due to data error.
We are indebted to Alison Kennedy from UNDP for helpful correspondence and providing the "revised" HDI statistics. We thank Jenny Aker, David Albouy, Werner Antweiler, Richard Carson, Maria Damon, Alain DeJanvry, Levis Kochin, James Rauch, Elisabeth Sadoulet, George Wright, the editor and two anonymous referees for many helpful comments. We gratefully acknowledge generous funding provided by a University of California's Institute on Global Conflict and Cooperation faculty research grant. All errors in this manuscript are the authors'. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research.
Hendrik Wolff & Howard Chong & Maximilian Auffhammer, 2011. "Classification, Detection and Consequences of Data Error: Evidence from the Human Development Index," Economic Journal, Royal Economic Society, vol. 121(553), pages 843-870, 06. citation courtesy of