R P Laursen1, S-M Dalskov1, C T Damsgaard1, C Ritz1. 1. Faculty of Science, Department of Nutrition, Exercise and Sports, University of Copenhagen, Copenhagen, Denmark.
Abstract
BACKGROUND/ OBJECTIVES: Transformation of outcomes is frequently used in the analysis of studies in clinical nutrition. However, back-transformation of estimated treatment means and differences is complicated by the nonlinear nature of the transformations. It is not straightforward to obtain an estimated treatment difference that can be interpreted without any reference to the additional predictors included in the statistical model; and moreover, standard errors are not easily available. The aim of this work was to provide a generally applicable, yet operational procedure for obtaining back-transformed estimated differences, and corresponding standard errors and 95% confidence intervals. SUBJECTS/ METHODS: Based on data from two randomized controlled studies and an exemplary data set that had all previously been published, we evaluated our approximate procedure by comparing results for different approaches for showing back-transformed estimated treatment differences. RESULTS: Estimated differences obtained on logarithm, square root and reciprocal square root-transformed scales were back-transformed into estimated differences on the original scales, and these estimates were in good agreement with the results reported by the original studies. CONCLUSIONS: The proposed approximate procedure provides a flexible approach for obtaining quite accurate back-transformed estimated differences in terms of medians and for deriving the corresponding standard errors.
BACKGROUND/ OBJECTIVES: Transformation of outcomes is frequently used in the analysis of studies in clinical nutrition. However, back-transformation of estimated treatment means and differences is complicated by the nonlinear nature of the transformations. It is not straightforward to obtain an estimated treatment difference that can be interpreted without any reference to the additional predictors included in the statistical model; and moreover, standard errors are not easily available. The aim of this work was to provide a generally applicable, yet operational procedure for obtaining back-transformed estimated differences, and corresponding standard errors and 95% confidence intervals. SUBJECTS/ METHODS: Based on data from two randomized controlled studies and an exemplary data set that had all previously been published, we evaluated our approximate procedure by comparing results for different approaches for showing back-transformed estimated treatment differences. RESULTS: Estimated differences obtained on logarithm, square root and reciprocal square root-transformed scales were back-transformed into estimated differences on the original scales, and these estimates were in good agreement with the results reported by the original studies. CONCLUSIONS: The proposed approximate procedure provides a flexible approach for obtaining quite accurate back-transformed estimated differences in terms of medians and for deriving the corresponding standard errors.
Authors: B L Burns-Whitmore; E H Haddad; J Sabaté; K Jaceldo-Siegl; J Tanzman; S Rajaram Journal: Eur J Clin Nutr Date: 2010-07-28 Impact factor: 4.016
Authors: P Thankachan; S Selvam; D Surendran; S Chellan; M Pauline; S A Abrams; A V Kurpad Journal: Eur J Clin Nutr Date: 2012-12-12 Impact factor: 4.016
Authors: Michael B Zimmermann; Sonja Y Hess; Luciano Molinari; Bruno De Benoist; François Delange; Lewis E Braverman; Kenji Fujieda; Yoshiya Ito; Pieter L Jooste; Khairya Moosa; Elizabeth N Pearce; Eduardo A Pretell; Yoshimasa Shishiba Journal: Am J Clin Nutr Date: 2004-02 Impact factor: 7.045
Authors: L B Sørensen; C T Damsgaard; R A Petersen; S-M Dalskov; M F Hjorth; C B Dyssegaard; N Egelund; I Tetens; A Astrup; L Lauritzen; K F Michaelsen Journal: Eur J Clin Nutr Date: 2016-06-15 Impact factor: 4.016
Authors: Marie T B Madsen; Anja P Biltoft-Jensen; Ellen Trolle; Lotte Lauritzen; Kim F Michaelsen; Camilla T Damsgaard Journal: Eur J Nutr Date: 2022-05-27 Impact factor: 4.865
Authors: Stine-Mathilde Dalskov; Christian Ritz; Anni Larnkjær; Camilla T Damsgaard; Rikke A Petersen; Louise B Sørensen; Mads F Hjorth; Ken K Ong; Arne Astrup; Christian Mølgaard; Kim F Michaelsen Journal: Pediatr Res Date: 2015-10-21 Impact factor: 3.756
Authors: Anne V Thorsen; Anne D Lassen; Elisabeth W Andersen; Lene M Christensen; Anja Biltoft-Jensen; Rikke Andersen; Camilla T Damsgaard; Kim F Michaelsen; Inge Tetens Journal: J Nutr Sci Date: 2015-05-06
Authors: Camilla T Damsgaard; Maj B Eidner; Ken D Stark; Mads F Hjorth; Anders Sjödin; Malene R Andersen; Rikke Andersen; Inge Tetens; Arne Astrup; Kim F Michaelsen; Lotte Lauritzen Journal: PLoS One Date: 2014-10-15 Impact factor: 3.240
Authors: Yuguang Lin; Wieneke P Koppenol; Diny Knol; Mario A Vermeer; Harry Hiemstra; Silvia Friedrichs; Dieter Lütjohann; Elke A Trautwein Journal: Nutrients Date: 2019-09-30 Impact factor: 5.717
Authors: Lisa Tussing-Humphreys; Melissa Lamar; Andrew McLeod; Linda Schiffer; Lara Blumstein; Roxanne Dakers; Aimee Karstens; Nefertiti Oji Njideka Hemphill; Desmona Strahan; Leilah Siegel; Jennifer Sanchez Flack; Mirjana Antonic; Leo Restrepo; Michael Berbaum; Marian Fitzgibbon Journal: Prev Med Rep Date: 2022-08-19
Authors: S Dalskov; C Ritz; A Larnkjær; C T Damsgaard; R A Petersen; L B Sørensen; K K Ong; A Astrup; K F Michaelsen; C Mølgaard Journal: Osteoporos Int Date: 2015-12-14 Impact factor: 4.507