Linear Regression Calibration: Theoretical Framework and Empirical Results in EPIC, Germany

Abstract

Large scale dietary assessment instruments are usually based on the food frequency technique and have therefore to be tailored to the involved populations with respect to mode of application and inquired food items. In multicenter studies with different populations, the direct comparability of dietary data is therefore a challenge because each local dietary assessment tool might have its specific measurement error. Thus, for risk analysis the direct use of dietary measurements across centers requires a common reference. For example, in the European prospective cohort study EPIC (European Prospective Investigation into Cancer and Nutrition) a 24-hour recall was chosen to serve as such a reference instrument which was based on a highly standardized computer-assisted interview (EPIC-SOFT). The 24-hour recall was applied to a representative subset of EPIC participants in all centers. The theoretical framework of combining multicenter dietary information was previously published in several papers and is called linear regression calibration. It is based on a linear regression of the food frequency questionnaire to the reference. The regression coefficients describe the absolute and proportional scaling bias of the questionnaire with the 24-hour recall taken as reference. This article describes the statistical basis of the calibration approach and presents first empirical results of its application to fruit, cereals and meat consumption in EPIC Germany represented by the two EPIC centers, Heidelberg and Potsdam. It was found that fruit could be measured well by the questionnaire in both centers (λcirc; = 0.98 (males) and λcirc; = 0.95 (females) in Heidelberg, and λcirc; = 0.86 (males) and λcirc; = 0.7 (females) in Potsdam), cereals less (λcirc; = 0.53 (males) and λcirc; = 0.4 (females) in Heidelberg, and λcirc; = 0.53 (males) and λcirc; = 0.44 (females) in Potsdam), and that the assessment of meat (λcirc; = 0.72 (males) and λcirc; = 0.65 (females) in Heidelberg, and λcirc; = 0.49 (males) and λcirc; = 0.42 (females) in Potsdam) has a center-specific bias. The application of the calibration approach to the questionnaire data will change the ranking of the two centers following the data of the reference instrument, and not well-measured food items will exhibit considerably less variation compared to the original data. We conclude that calibration is a necessary step in multicenter studies. However, this exercise shows that the current statistical framework is not yet sufficiently developed for a broad application.

Aplicação de regressão linear para correção de dados dietéticos

“…Extreme values are especially affected by linear correction due to the assumption of linearity between the reference method and the questionnaire. 13 Fraser and Stram 7 , demonstrated the present bias when crude FFQ data are used in a multivariate regression to estimate the effect of diet in disease and it is essentially eliminated by a calibration regression. Thus, the use of FFQA in epidemiological studies without correction, may lead to the above described situation.…”

“…This statistical methodology aims at making measures obtained at FFQ closer to real intake values, estimated by reference methods supposedly free from biases (systematic errors), and it is not necessarily applied more than once. 13 Thus, corrected values are obtained, partially free from the errors present in FFQ.…”

“…4,14,18 This approach is performed a priori, from the parametric or non-parametric regression model. 10,13,14 Among the parametric methods, calibration using linear regression model 14 is considered as the standard: 17 and intake estimate obtained by the reference method is modeled as a function of the FFQ intake. Linear regression model obtained in the calibration study may be used as a predictor model to estimate real intake, from a FFQ value.…”

Reprodutibilidade, validade relativa e calibração de um questionário de frequência alimentar para adultos da Região Metropolitana de Porto Alegre, Rio Grande do Sul, Brasil

“…Entre eles estão os coeficientes de correlação, classificação em categorias de ingestão alimentar (quartis ou quintis) em cada método e o método proposto por Bland & Altman 8 , que avalia a concordância entre os métodos por meio da média das diferenças entre eles 8,9,10 . Os estudos de calibração, por sua vez, servem para aproximar os dados obtidos com o QFA aos valores do método de referência 11 .…”

Calibration of the dietary data obtained from the Brazilian center of the Natural History of HPV Infection in Men study: the HIM Study

“…Knowing that error is inherent in food intake measurements, methodological strategies have been developed in an attempt to make the measurements obtained through the QFFQ closer to the quantities actually consumed, which are estimated through reference methods that are supposedly error-free 4,5 . This methodology is called calibration and it basically can be seen as a scale adjustment to the questionnaire measurements 6 .…”