Analysis of the benefits of a Mediterranean diet in the GISSI-Prevenzione study: A case study in imputation of missing values from repeated measurements

Federica Barzi, Mark Woodward, Rosa Maria Marfisi, Gianni Tognoni, Roberto Marchioli

Research output: Contribution to journalArticle

Abstract

The problem of missing values has increasingly being recognized in epidemiology. New methods allow for the analysis of missing data that can provide valid estimates of epidemiological quantities of interest. The GISSI-Prevenzione study was aimed to reliably assess the long-term relationship between the consumption of foods typical of the Mediterranean diet and the risk of mortality amongst 11,323 Italians with prior myocardial infarction. Food intake frequencies were recorded repeatedly over the 4.5 years of follow-up and missing values affected each food variable at increasing rates over the course of the study. Comparisons were made between the results obtained from the analysis of the complete data and those obtained after imputing the missing data with simple imputation methods and with various implementations of the multiple imputation (MI) method. MI appeared to best address the issue of missing data on the food intake frequencies, preserving the observed distributions and relationships between variables whilst producing plausible estimates of variability. Given its theoretical properties and flexibility to different types of data, MI is more likely to provide valid estimates, compared to complete data analysis and imputation by simple methods, and is thus worthy of wider consideration amongst epidemiological researchers.

Original languageEnglish (US)
Pages (from-to)15-24
Number of pages10
JournalEuropean Journal of Epidemiology
Volume21
Issue number1
DOIs
StatePublished - Jan 2006
Externally publishedYes

Fingerprint

Mediterranean Diet
Eating
Food
Epidemiology
Myocardial Infarction
Research Personnel
Mortality

Keywords

  • Imputation
  • Longitudinal study
  • Mediterranean diet
  • Missing values
  • Mortality
  • Odds ratio

ASJC Scopus subject areas

  • Epidemiology

Cite this

Analysis of the benefits of a Mediterranean diet in the GISSI-Prevenzione study : A case study in imputation of missing values from repeated measurements. / Barzi, Federica; Woodward, Mark; Marfisi, Rosa Maria; Tognoni, Gianni; Marchioli, Roberto.

In: European Journal of Epidemiology, Vol. 21, No. 1, 01.2006, p. 15-24.

Research output: Contribution to journalArticle

Barzi, Federica ; Woodward, Mark ; Marfisi, Rosa Maria ; Tognoni, Gianni ; Marchioli, Roberto. / Analysis of the benefits of a Mediterranean diet in the GISSI-Prevenzione study : A case study in imputation of missing values from repeated measurements. In: European Journal of Epidemiology. 2006 ; Vol. 21, No. 1. pp. 15-24.
@article{6f57080f840441d2a74d6c486c9000d2,
title = "Analysis of the benefits of a Mediterranean diet in the GISSI-Prevenzione study: A case study in imputation of missing values from repeated measurements",
abstract = "The problem of missing values has increasingly being recognized in epidemiology. New methods allow for the analysis of missing data that can provide valid estimates of epidemiological quantities of interest. The GISSI-Prevenzione study was aimed to reliably assess the long-term relationship between the consumption of foods typical of the Mediterranean diet and the risk of mortality amongst 11,323 Italians with prior myocardial infarction. Food intake frequencies were recorded repeatedly over the 4.5 years of follow-up and missing values affected each food variable at increasing rates over the course of the study. Comparisons were made between the results obtained from the analysis of the complete data and those obtained after imputing the missing data with simple imputation methods and with various implementations of the multiple imputation (MI) method. MI appeared to best address the issue of missing data on the food intake frequencies, preserving the observed distributions and relationships between variables whilst producing plausible estimates of variability. Given its theoretical properties and flexibility to different types of data, MI is more likely to provide valid estimates, compared to complete data analysis and imputation by simple methods, and is thus worthy of wider consideration amongst epidemiological researchers.",
keywords = "Imputation, Longitudinal study, Mediterranean diet, Missing values, Mortality, Odds ratio",
author = "Federica Barzi and Mark Woodward and Marfisi, {Rosa Maria} and Gianni Tognoni and Roberto Marchioli",
year = "2006",
month = "1",
doi = "10.1007/s10654-005-5086-5",
language = "English (US)",
volume = "21",
pages = "15--24",
journal = "European Journal of Epidemiology",
issn = "0393-2990",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Analysis of the benefits of a Mediterranean diet in the GISSI-Prevenzione study

T2 - A case study in imputation of missing values from repeated measurements

AU - Barzi, Federica

AU - Woodward, Mark

AU - Marfisi, Rosa Maria

AU - Tognoni, Gianni

AU - Marchioli, Roberto

PY - 2006/1

Y1 - 2006/1

N2 - The problem of missing values has increasingly being recognized in epidemiology. New methods allow for the analysis of missing data that can provide valid estimates of epidemiological quantities of interest. The GISSI-Prevenzione study was aimed to reliably assess the long-term relationship between the consumption of foods typical of the Mediterranean diet and the risk of mortality amongst 11,323 Italians with prior myocardial infarction. Food intake frequencies were recorded repeatedly over the 4.5 years of follow-up and missing values affected each food variable at increasing rates over the course of the study. Comparisons were made between the results obtained from the analysis of the complete data and those obtained after imputing the missing data with simple imputation methods and with various implementations of the multiple imputation (MI) method. MI appeared to best address the issue of missing data on the food intake frequencies, preserving the observed distributions and relationships between variables whilst producing plausible estimates of variability. Given its theoretical properties and flexibility to different types of data, MI is more likely to provide valid estimates, compared to complete data analysis and imputation by simple methods, and is thus worthy of wider consideration amongst epidemiological researchers.

AB - The problem of missing values has increasingly being recognized in epidemiology. New methods allow for the analysis of missing data that can provide valid estimates of epidemiological quantities of interest. The GISSI-Prevenzione study was aimed to reliably assess the long-term relationship between the consumption of foods typical of the Mediterranean diet and the risk of mortality amongst 11,323 Italians with prior myocardial infarction. Food intake frequencies were recorded repeatedly over the 4.5 years of follow-up and missing values affected each food variable at increasing rates over the course of the study. Comparisons were made between the results obtained from the analysis of the complete data and those obtained after imputing the missing data with simple imputation methods and with various implementations of the multiple imputation (MI) method. MI appeared to best address the issue of missing data on the food intake frequencies, preserving the observed distributions and relationships between variables whilst producing plausible estimates of variability. Given its theoretical properties and flexibility to different types of data, MI is more likely to provide valid estimates, compared to complete data analysis and imputation by simple methods, and is thus worthy of wider consideration amongst epidemiological researchers.

KW - Imputation

KW - Longitudinal study

KW - Mediterranean diet

KW - Missing values

KW - Mortality

KW - Odds ratio

UR - http://www.scopus.com/inward/record.url?scp=31944440734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=31944440734&partnerID=8YFLogxK

U2 - 10.1007/s10654-005-5086-5

DO - 10.1007/s10654-005-5086-5

M3 - Article

C2 - 16450202

AN - SCOPUS:31944440734

VL - 21

SP - 15

EP - 24

JO - European Journal of Epidemiology

JF - European Journal of Epidemiology

SN - 0393-2990

IS - 1

ER -