Limits...
Log-transformation and its implications for data analysis.

Feng C, Wang H, Lu N, Chen T, He H, Lu Y, Tu XM - Shanghai Arch Psychiatry (2014)

Bottom Line: This paper highlights serious problems in this classic approach for dealing with skewed data.Moreover, the results of standard statistical tests performed on log-transformed data are often not relevant for the original, non-transformed data.We demonstrate these problems by presenting examples that use simulated data.Abstract available from the publisher.

View Article: PubMed Central - PubMed

Affiliation: Department of Biostatistics and Computational Biology,University of Rochester, Rochester, NY, USA.

ABSTRACT

Summary: The log-transformation is widely used in biomedical and psychosocial research to deal with skewed data. This paper highlights serious problems in this classic approach for dealing with skewed data. Despite the common belief that the log transformation can decrease the variability of data and make data conform more closely to the normal distribution, this is usually not the case. Moreover, the results of standard statistical tests performed on log-transformed data are often not relevant for the original, non-transformed data.We demonstrate these problems by presenting examples that use simulated data. We conclude that if used at all, data transformations must be applied very cautiously. We recommend that in most circumstances researchers abandon these traditional methods of dealing with skewed data and, instead, use newer analytic methods that are not dependent on the distribution the data, such as generalized estimating equations (GEE).

No MeSH data available.


Related in: MedlinePlus

Histograms of original data (left plot) and log-transformed data (right plot) from a simulation study that examines the effect of log-transformation on reducing skewness.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4120293&req=5

sap-26-02-105-g002: Histograms of original data (left plot) and log-transformed data (right plot) from a simulation study that examines the effect of log-transformation on reducing skewness.


Log-transformation and its implications for data analysis.

Feng C, Wang H, Lu N, Chen T, He H, Lu Y, Tu XM - Shanghai Arch Psychiatry (2014)

Histograms of original data (left plot) and log-transformed data (right plot) from a simulation study that examines the effect of log-transformation on reducing skewness.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4120293&req=5

sap-26-02-105-g002: Histograms of original data (left plot) and log-transformed data (right plot) from a simulation study that examines the effect of log-transformation on reducing skewness.
Bottom Line: This paper highlights serious problems in this classic approach for dealing with skewed data.Moreover, the results of standard statistical tests performed on log-transformed data are often not relevant for the original, non-transformed data.We demonstrate these problems by presenting examples that use simulated data.Abstract available from the publisher.

View Article: PubMed Central - PubMed

Affiliation: Department of Biostatistics and Computational Biology,University of Rochester, Rochester, NY, USA.

ABSTRACT

Summary: The log-transformation is widely used in biomedical and psychosocial research to deal with skewed data. This paper highlights serious problems in this classic approach for dealing with skewed data. Despite the common belief that the log transformation can decrease the variability of data and make data conform more closely to the normal distribution, this is usually not the case. Moreover, the results of standard statistical tests performed on log-transformed data are often not relevant for the original, non-transformed data.We demonstrate these problems by presenting examples that use simulated data. We conclude that if used at all, data transformations must be applied very cautiously. We recommend that in most circumstances researchers abandon these traditional methods of dealing with skewed data and, instead, use newer analytic methods that are not dependent on the distribution the data, such as generalized estimating equations (GEE).

No MeSH data available.


Related in: MedlinePlus