Abstract
1. Ecological count data (e.g., number of individuals or species) are often log-transformed to satisfy parametric test assumptions.2. Apart from the fact that generalized linear models are better suited in dealing with count data, a log-transformation of counts has the additional quandary in how to deal with zero observations. With just one zero observation (if this observation represents a sampling unit), the whole dataset needs to be fudged by adding a value (usually 1) before transformation. 3. Simulating data from a negative binomial distribution, we compared the outcome of fitting models that were transformed in various ways (log, square-root) with results from fitting models using Poisson and negative binomial models to untransformed count data. 4. We found that the transformations performed poorly, except when the dispersion was small and the mean counts were large. The Poisson and negative binomial models consistently performed well, with little bias.
Similar content being viewed by others
Article PDF
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
O'Hara, R., Kotze, J. Do not log-transform count data . Nat Prec (2010). https://doi.org/10.1038/npre.2010.4136.1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/npre.2010.4136.1
Keywords
This article is cited by
-
Overcoming limitations to propagation from seed of 40 Australian species important for restoration
New Forests (2023)
-
To delegate or not to delegate? On the quality of voluntary corporate financial disclosure
Review of Managerial Science (2022)
-
Internal governance and corporate acquisition activities
Eurasian Business Review (2022)
-
Cultural Change Reduces Gender Differences in Mobility and Spatial Ability among Seminomadic Pastoralist-Forager Children in Northern Namibia
Human Nature (2021)