@techreport{NBERt0246,
title = "Estimating Log Models: To Transform or Not to Transform?",
author = "Willard G. Manning and John Mullahy",
institution = "National Bureau of Economic Research",
type = "Working Paper",
series = "Technical Working Paper Series",
number = "246",
year = "1999",
month = "November",
doi = {10.3386/t0246},
URL = "http://www.nber.org/papers/t0246",
abstract = {Data on health care expenditures, length of stay, utilization of health services, consumption of unhealthy commodities, etc. are typically characterized by: (a) nonnegative outcomes; (b) nontrivial fractions of zero outcomes in the population (and sample); and (c) positively-skewed distributions of the nonzero realizations. Similar data structures are encountered in labor economics as well. This paper provides simulation-based evidence on the finite-sample behavior of two sets of estimators designed to look at the effect of a set of covariates x on the expected outcome, E(y|x), under a range of data problems encountered in every day practice: generalized linear models (GLM), a subset of which can simply be viewed as differentially weighted nonlinear least-squares estimators, and those derived from least-squares estimators for the ln(y). We consider the first- and second- order behavior of these candidate estimators under alternative assumptions on the data generating processes. Our results indicate that the choice of estimator for models of ln(E(x|y)) can have major implications for empirical results if the estimator is not designed to deal with the specific data generating mechanism. Garden-variety statistical problems - skewness, kurtosis, and heteroscedasticity - can lead to an appreciable bias for some estimators or appreciable losses in precision for others.},
}