# A distributional approach to obtain adjusted comparisons of proportions of a population at risk

Sauzet O, Breckenkamp J, Borde T, Brenne S, David M, Razum O, Peacock JL (2016) *Emerg Themes Epidemiol* 13: 8.

Download

bmc.sauzet.016-0050-2.pdf
943.89 KB

*Journal Article*|

*Original Article*|

*Published*|

*English*

Author

Sauzet, Odile

^{UniBi}; Breckenkamp, Jürgen^{UniBi}; Borde, Theda ; Brenne, Silke ; David, Matthias ; Razum, Oliver^{UniBi}; Peacock, Janet L.Department

Abstract

Background
Dichotomisation of continuous data has statistical drawbacks such as loss of power but may be useful in epidemiological research to define high risk individuals.
Methods
We extend a methodology for the presentation of comparison of proportions derived from a comparison of means for a continuous outcome to reflect the relationship between a continuous outcome and covariates in a linear (mixed) model without losing statistical power. The so called “distributional method” is described and using perinatal data for illustration, results from the distributional method are compared to those of logistic regression and to quantile regression for three different outcomes.
Results
Estimates obtained using the distributional method for the comparison of proportions are consistently more precise than those obtained using logistic regression. For one of the three outcomes the estimates obtained from the distributional method and from logistic regression disagreed highlighting that the relationships between outcome and covariate differ conceptually between the two models.
Conclusion
When an outcome follows the required condition of distribution shift between exposure groups, the results of a linear regression model can be followed by the corresponding comparison of proportions at risk. This dual approach provides more precise estimates than logistic regression thus avoiding the drawback of the usual dichotomisation of continuous outcomes.

Publishing Year

ISSN

Financial disclosure

Article Processing Charge funded by the Deutsche Forschungsgemeinschaft and the Open Access Publication Fund of Bielefeld University.

PUB-ID

### Cite this

Sauzet O, Breckenkamp J, Borde T, et al. A distributional approach to obtain adjusted comparisons of proportions of a population at risk.

*Emerg Themes Epidemiol*. 2016;13:8.Sauzet, O., Breckenkamp, J., Borde, T., Brenne, S., David, M., Razum, O., & Peacock, J. L. (2016). A distributional approach to obtain adjusted comparisons of proportions of a population at risk.

*Emerg Themes Epidemiol*,*13*, 8. doi:10.1186/s12982-016-0050-2Sauzet, O., Breckenkamp, J., Borde, T., Brenne, S., David, M., Razum, O., and Peacock, J. L. (2016). A distributional approach to obtain adjusted comparisons of proportions of a population at risk.

*Emerg Themes Epidemiol*13, 8.Sauzet, O., et al., 2016. A distributional approach to obtain adjusted comparisons of proportions of a population at risk.

*Emerg Themes Epidemiol*, 13, p 8. O. Sauzet, et al., “A distributional approach to obtain adjusted comparisons of proportions of a population at risk”,

*Emerg Themes Epidemiol*, vol. 13, 2016, pp. 8. Sauzet, O., Breckenkamp, J., Borde, T., Brenne, S., David, M., Razum, O., Peacock, J.L.: A distributional approach to obtain adjusted comparisons of proportions of a population at risk. Emerg Themes Epidemiol. 13, 8 (2016).

Sauzet, Odile, Breckenkamp, Jürgen, Borde, Theda, Brenne, Silke, David, Matthias, Razum, Oliver, and Peacock, Janet L. “A distributional approach to obtain adjusted comparisons of proportions of a population at risk”.

*Emerg Themes Epidemiol*13 (2016): 8.**All files available under the following license(s):**

**Copyright Statement:**

**This Item is protected by copyright and/or related rights.**[...]

**Main File(s)**

File Name

bmc.sauzet.016-0050-2.pdf
943.89 KB

Access Level

Open Access

Last Uploaded

2016-06-13T14:33:35Z

This data publication is cited in the following publications:

This publication cites the following data publications:

### 24 References

Data provided by Europe PubMed Central.

Dichotomizing continuous outcome variables: dependence of the magnitude of association and statistical power on the cutpoint

Ragland DR., 1992

Ragland DR., 1992

The cost of dichotomising continuous variables.

Altman DG, Royston P.,

PMID: 16675816

Altman DG, Royston P.,

*BMJ*332(7549), 2006PMID: 16675816

Odd odds interactions introduced through dichotomisation of continuous outcomes.

Breitling LP, Brenner H.,

PMID: 19692723

Breitling LP, Brenner H.,

*J Epidemiol Community Health*64(4), 2010PMID: 19692723

How weight change is modelled in population studies can affect research findings: empirical results from a large-scale cohort study.

Paige E, Korda RJ, Banks E, Rodgers B.,

PMID: 24907245

Paige E, Korda RJ, Banks E, Rodgers B.,

*BMJ Open*4(6), 2014PMID: 24907245

Dichotomising continuous data while retaining statistical power using a distributional approach.

Peacock JL, Sauzet O, Ewings SM, Kerry SM.,

PMID: 22865598

Peacock JL, Sauzet O, Ewings SM, Kerry SM.,

*Stat Med*31(26), 2012PMID: 22865598

Casella G, Berger RL., 1990

Estimating dichotomised outcomes in two groups with unequal variances: a distributional approach.

Sauzet O, Peacock JL.,

PMID: 24989698

Sauzet O, Peacock JL.,

*Stat Med*33(26), 2014PMID: 24989698

Comparison of Perinatal Data of Immigrant Women of Turkish Origin and German Women - Results of a Prospective Study in Berlin.

David M, Borde T, Brenne S, Ramsauer B, Henrich W, Breckenkamp J, Razum O.,

PMID: 25089056

David M, Borde T, Brenne S, Ramsauer B, Henrich W, Breckenkamp J, Razum O.,

*Geburtshilfe Frauenheilkd*74(5), 2014PMID: 25089056

Smoking during pregnancy among Turkish immigrants in Germany-are there associations with acculturation?

Reiss K, Breckenkamp J, Borde T, Brenne S, David M, Razum O.,

PMID: 25468901

Reiss K, Breckenkamp J, Borde T, Brenne S, David M, Razum O.,

*Nicotine Tob. Res.*17(6), 2015PMID: 25468901

AUTHOR UNKNOWN, 0

Dichotomisation of a continuous outcome and effect on meta-analyses: illustration of the distributional approach using the outcome birthweight.

Ofuya M, Sauzet O, Peacock JL.,

PMID: 24920271

Ofuya M, Sauzet O, Peacock JL.,

*Syst Rev*3(), 2014PMID: 24920271

Dichotomisation using a distributional approach when the outcome is skewed.

Sauzet O, Ofuya M, Peacock JL.,

PMID: 25902850

Sauzet O, Ofuya M, Peacock JL.,

*BMC Med Res Methodol*15(), 2015PMID: 25902850

A global reference for fetal-weight and birthweight percentiles.

Mikolajczyk RT, Zhang J, Betran AP, Souza JP, Mori R, Gulmezoglu AM, Merialdi M.,

PMID: 21621717

Mikolajczyk RT, Zhang J, Betran AP, Souza JP, Mori R, Gulmezoglu AM, Merialdi M.,

*Lancet*377(9780), 2011PMID: 21621717

AUTHOR UNKNOWN, 0

Modelling the hierarchical structure in datasets with very small clusters: a simulation study to explore the effect of the proportion of clusters when the outcome is continuous.

Sauzet O, Wright KC, Marston L, Brocklehurst P, Peacock JL.,

PMID: 23027676

Sauzet O, Wright KC, Marston L, Brocklehurst P, Peacock JL.,

*Stat Med*32(8), 2013PMID: 23027676

Koenker R., 2005

AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

On the importance--and the unimportance--of birthweight.

Wilcox AJ.,

PMID: 11821313

Wilcox AJ.,

*Int J Epidemiol*30(6), 2001PMID: 11821313

Multivariate Meta-Analysis of Heterogeneous Studies Using Only Summary Statistics: Efficiency and Robustness.

Liu D, Liu R, Xie M.,

PMID: 26190875

Liu D, Liu R, Xie M.,

*J Am Stat Assoc*110(509), 2015PMID: 26190875

AUTHOR UNKNOWN, 0

Logistic regression: why we cannot do what we think we can do, and what we can do about it

Mood C., 2010

Mood C., 2010

Misclassification

Gustafson P, Greenland S., 2014

Gustafson P, Greenland S., 2014

A note on dichotomization of continuous response variable in the presence of contamination and model misspecification.

Shentu Y, Xie M.,

PMID: 20812301

Shentu Y, Xie M.,

*Stat Med*29(21), 2010PMID: 20812301

### Export

0 Marked Publications### Web of Science

View record in Web of Science®### Sources

PMID: 27279891

PubMed | Europe PMC