Cornelia Weikert1, Matthias B Schulze. 1. aFederal Institute for Risk Assessment, Department of Food Safety, Berlin bInstitute for Social Medicine, Epidemiology and Health Economics, Charité University Medical Center, Berlin cDepartment of Molecular Epidemiology, German Institute of Human Nutrition Potsdam-Rehbruecke, Nuthetal, Germany.
Abstract
PURPOSE OF REVIEW: The purpose of review is to present methodological issues as well as most relevant recent developments on the application of a statistical method to derive dietary patterns: reduced rank regression (RRR). RRR can be used efficiently in nutritional epidemiology to identify dietary patterns associated with selected response variables that have known relations with a disease outcome of interest. This has the advantage of building on a priori knowledge of biological relations, by including plausible intermediates between diet and the outcome of interest. RECENT FINDINGS: This statistical method has been applied first in nutritional epidemiology about 1 decade ago. Since then, more than 60 publications were published applying the RRR. This method is considerably dependent on an adequate selection of response variables. These response sets were most often a combination of nutrients or of selected endogenous biomarkers. But also variables of intermediate clinical phenotype or contaminants were selected. However, applying this method, several methodological issues, such as, for example, selection of responses, simplification, and validation of the derived pattern should be taken into account. SUMMARY: RRR is a modern statistical method to derive dietary patterns that can be used to test specific hypothesis on pathways from diet to development of a disease.
PURPOSE OF REVIEW: The purpose of review is to present methodological issues as well as most relevant recent developments on the application of a statistical method to derive dietary patterns: reduced rank regression (RRR). RRR can be used efficiently in nutritional epidemiology to identify dietary patterns associated with selected response variables that have known relations with a disease outcome of interest. This has the advantage of building on a priori knowledge of biological relations, by including plausible intermediates between diet and the outcome of interest. RECENT FINDINGS: This statistical method has been applied first in nutritional epidemiology about 1 decade ago. Since then, more than 60 publications were published applying the RRR. This method is considerably dependent on an adequate selection of response variables. These response sets were most often a combination of nutrients or of selected endogenous biomarkers. But also variables of intermediate clinical phenotype or contaminants were selected. However, applying this method, several methodological issues, such as, for example, selection of responses, simplification, and validation of the derived pattern should be taken into account. SUMMARY: RRR is a modern statistical method to derive dietary patterns that can be used to test specific hypothesis on pathways from diet to development of a disease.
Authors: Franziska Jannasch; Janine Kröger; Claudia Agnoli; Aurelio Barricarte; Heiner Boeing; Valerie Cayssials; Sandra Colorado-Yohar; Christina C Dahm; Courtney Dow; Guy Fagherazzi; Paul W Franks; Heinz Freisling; Marc J Gunter; Nicola D Kerrison; Timothy J Key; Kay-Tee Khaw; Tilman Kühn; Cecilie Kyro; Francesca Romana Mancini; Olatz Mokoroa; Peter Nilsson; Kim Overvad; Domenico Palli; Salvatore Panico; Jose Ramón Quirós García; Olov Rolandsson; Carlotta Sacerdote; Mariá-José Sánchez; Mohammad Sediq Sahrai; Ruth Schübel; Ivonne Sluijs; Annemieke M W Spijkerman; Anne Tjonneland; Tammy Y N Tong; Rosario Tumino; Elio Riboli; Claudia Langenberg; Stephen J Sharp; Nita G Forouhi; Matthias B Schulze; Nicholas J Wareham Journal: J Nutr Date: 2019-06-01 Impact factor: 4.798
Authors: Matthew K Taylor; Debra K Sullivan; Edward F Ellerbeck; Byron J Gajewski; Heather D Gibbs Journal: Public Health Nutr Date: 2019-05-31 Impact factor: 4.022
Authors: Randi K Johnson; Lauren A Vanderlinden; Brian C DeFelice; Ulla Uusitalo; Jennifer Seifert; Sili Fan; Tessa Crume; Oliver Fiehn; Marian Rewers; Katerina Kechris; Jill M Norris Journal: Pediatr Diabetes Date: 2020-08-09 Impact factor: 4.866
Authors: E Vermeulen; K Stronks; M Visser; I A Brouwer; M B Snijder; R J T Mocking; E M Derks; A H Schene; M Nicolaou Journal: Eur J Clin Nutr Date: 2017-05-03 Impact factor: 4.016
Authors: Kristin J Marks; Kate Northstone; Eleni Papadopoulou; Anne Lise Brantsæter; Line Småstuen Haug; Penelope P Howards; Melissa M Smarr; W Dana Flanders; Terryl J Hartman Journal: Environ Adv Date: 2021-12
Authors: Romy F Willemsen; Jessica McNeil; Emily Heer; Steven T Johnson; Christine M Friedenreich; Darren R Brenner Journal: Eur J Clin Nutr Date: 2021-06-24 Impact factor: 4.016
Authors: Merel J Huisman; Sabita S Soedamah-Muthu; Esther Vermeulen; Mirthe Muilwijk; Marieke B Snijder; Mary N Nicolaou; Irene G M van Valkengoed Journal: Nutrients Date: 2018-01-15 Impact factor: 5.717