Statistical approaches for assessing the relative validity of a food-frequency questionnaire: use of correlation coefficients and the kappa statistic

Lindsey Fiona Masson, Geraldine McNeill, J. O. Tomany, J. A. Simpson, Heather Sinclair Peace, L. Wei, D. A. Grubb, C. Bolton-Smith

Research output: Contribution to journalArticle

239 Citations (Scopus)

Abstract

Objective: To compare different statistical methods for assessing the relative validity of a self-administered, 150-item, semi-quantitative food-frequency questionnaire (FFQ) with 4-day weighed diet records (WR).

Design: Subjects completed the Scottish Collaborative Group FFQ and carried out a 4-day WR. Relative agreement between the FFQ and WR for energy-adjusted nutrient intakes was assessed by Pearson and Spearman rank correlation coefficients, the percentages of subjects classified into the same and opposite thirds of intake, and Cohen's weighted kappa.

Subjects: Forty-one men, mean age 36 (range 21-56) years, and 40 women, mean age 33 (range 19-58) years, recruited from different locations in Aberdeen, Scotland.

Results: Spearman correlation coefficients tended to be lower than Pearson correlation coefficients, and were above 0.5 for 10 of the 27 nutrients in men and 17 of the 27 nutrients in women. For nutrients with Spearman correlation coefficients above 0.5, the percentage of subjects correctly classified into thirds ranged from 39 to 78%, and weighted kappa values ranged from 0.23 to 0.66.

Conclusions: Both Spearman correlation coefficients and weighted kappa values are useful in assessing the relative validity of. estimates of nutrient intake by FFQs. Spearman correlation coefficients above 0.5, more than 50% of subjects correctly classified and less than 10% of subjects grossly misclassified into thirds, and weighted kappa values above 0.4 are recommended for nutrients of interest in epidemiological studies.

Original languageEnglish
Pages (from-to)313-321
Number of pages8
JournalPublic Health Nutrition
Volume6
Issue number3
DOIs
Publication statusPublished - 2003

Keywords

  • correlation coefficients
  • kappa statistic
  • food-frequency questionnaire
  • relative validity
  • weighed diet records
  • epidemiological methods
  • dietary assessment
  • ENERGY-INTAKE
  • GUIDELINES
  • VALIDATION
  • DIET

Cite this

Statistical approaches for assessing the relative validity of a food-frequency questionnaire: use of correlation coefficients and the kappa statistic. / Masson, Lindsey Fiona; McNeill, Geraldine; Tomany, J. O.; Simpson, J. A.; Peace, Heather Sinclair; Wei, L.; Grubb, D. A.; Bolton-Smith, C.

In: Public Health Nutrition, Vol. 6, No. 3, 2003, p. 313-321.

Research output: Contribution to journalArticle

Masson, Lindsey Fiona ; McNeill, Geraldine ; Tomany, J. O. ; Simpson, J. A. ; Peace, Heather Sinclair ; Wei, L. ; Grubb, D. A. ; Bolton-Smith, C. / Statistical approaches for assessing the relative validity of a food-frequency questionnaire: use of correlation coefficients and the kappa statistic. In: Public Health Nutrition. 2003 ; Vol. 6, No. 3. pp. 313-321.
@article{3a69690f8653494f94e47586a46610de,
title = "Statistical approaches for assessing the relative validity of a food-frequency questionnaire: use of correlation coefficients and the kappa statistic",
abstract = "Objective: To compare different statistical methods for assessing the relative validity of a self-administered, 150-item, semi-quantitative food-frequency questionnaire (FFQ) with 4-day weighed diet records (WR).Design: Subjects completed the Scottish Collaborative Group FFQ and carried out a 4-day WR. Relative agreement between the FFQ and WR for energy-adjusted nutrient intakes was assessed by Pearson and Spearman rank correlation coefficients, the percentages of subjects classified into the same and opposite thirds of intake, and Cohen's weighted kappa.Subjects: Forty-one men, mean age 36 (range 21-56) years, and 40 women, mean age 33 (range 19-58) years, recruited from different locations in Aberdeen, Scotland.Results: Spearman correlation coefficients tended to be lower than Pearson correlation coefficients, and were above 0.5 for 10 of the 27 nutrients in men and 17 of the 27 nutrients in women. For nutrients with Spearman correlation coefficients above 0.5, the percentage of subjects correctly classified into thirds ranged from 39 to 78{\%}, and weighted kappa values ranged from 0.23 to 0.66.Conclusions: Both Spearman correlation coefficients and weighted kappa values are useful in assessing the relative validity of. estimates of nutrient intake by FFQs. Spearman correlation coefficients above 0.5, more than 50{\%} of subjects correctly classified and less than 10{\%} of subjects grossly misclassified into thirds, and weighted kappa values above 0.4 are recommended for nutrients of interest in epidemiological studies.",
keywords = "correlation coefficients, kappa statistic, food-frequency questionnaire, relative validity, weighed diet records, epidemiological methods, dietary assessment, ENERGY-INTAKE, GUIDELINES, VALIDATION, DIET",
author = "Masson, {Lindsey Fiona} and Geraldine McNeill and Tomany, {J. O.} and Simpson, {J. A.} and Peace, {Heather Sinclair} and L. Wei and Grubb, {D. A.} and C. Bolton-Smith",
year = "2003",
doi = "10.1079/PHN2002429",
language = "English",
volume = "6",
pages = "313--321",
journal = "Public Health Nutrition",
issn = "1368-9800",
publisher = "Cambridge University Press",
number = "3",

}

TY - JOUR

T1 - Statistical approaches for assessing the relative validity of a food-frequency questionnaire: use of correlation coefficients and the kappa statistic

AU - Masson, Lindsey Fiona

AU - McNeill, Geraldine

AU - Tomany, J. O.

AU - Simpson, J. A.

AU - Peace, Heather Sinclair

AU - Wei, L.

AU - Grubb, D. A.

AU - Bolton-Smith, C.

PY - 2003

Y1 - 2003

N2 - Objective: To compare different statistical methods for assessing the relative validity of a self-administered, 150-item, semi-quantitative food-frequency questionnaire (FFQ) with 4-day weighed diet records (WR).Design: Subjects completed the Scottish Collaborative Group FFQ and carried out a 4-day WR. Relative agreement between the FFQ and WR for energy-adjusted nutrient intakes was assessed by Pearson and Spearman rank correlation coefficients, the percentages of subjects classified into the same and opposite thirds of intake, and Cohen's weighted kappa.Subjects: Forty-one men, mean age 36 (range 21-56) years, and 40 women, mean age 33 (range 19-58) years, recruited from different locations in Aberdeen, Scotland.Results: Spearman correlation coefficients tended to be lower than Pearson correlation coefficients, and were above 0.5 for 10 of the 27 nutrients in men and 17 of the 27 nutrients in women. For nutrients with Spearman correlation coefficients above 0.5, the percentage of subjects correctly classified into thirds ranged from 39 to 78%, and weighted kappa values ranged from 0.23 to 0.66.Conclusions: Both Spearman correlation coefficients and weighted kappa values are useful in assessing the relative validity of. estimates of nutrient intake by FFQs. Spearman correlation coefficients above 0.5, more than 50% of subjects correctly classified and less than 10% of subjects grossly misclassified into thirds, and weighted kappa values above 0.4 are recommended for nutrients of interest in epidemiological studies.

AB - Objective: To compare different statistical methods for assessing the relative validity of a self-administered, 150-item, semi-quantitative food-frequency questionnaire (FFQ) with 4-day weighed diet records (WR).Design: Subjects completed the Scottish Collaborative Group FFQ and carried out a 4-day WR. Relative agreement between the FFQ and WR for energy-adjusted nutrient intakes was assessed by Pearson and Spearman rank correlation coefficients, the percentages of subjects classified into the same and opposite thirds of intake, and Cohen's weighted kappa.Subjects: Forty-one men, mean age 36 (range 21-56) years, and 40 women, mean age 33 (range 19-58) years, recruited from different locations in Aberdeen, Scotland.Results: Spearman correlation coefficients tended to be lower than Pearson correlation coefficients, and were above 0.5 for 10 of the 27 nutrients in men and 17 of the 27 nutrients in women. For nutrients with Spearman correlation coefficients above 0.5, the percentage of subjects correctly classified into thirds ranged from 39 to 78%, and weighted kappa values ranged from 0.23 to 0.66.Conclusions: Both Spearman correlation coefficients and weighted kappa values are useful in assessing the relative validity of. estimates of nutrient intake by FFQs. Spearman correlation coefficients above 0.5, more than 50% of subjects correctly classified and less than 10% of subjects grossly misclassified into thirds, and weighted kappa values above 0.4 are recommended for nutrients of interest in epidemiological studies.

KW - correlation coefficients

KW - kappa statistic

KW - food-frequency questionnaire

KW - relative validity

KW - weighed diet records

KW - epidemiological methods

KW - dietary assessment

KW - ENERGY-INTAKE

KW - GUIDELINES

KW - VALIDATION

KW - DIET

U2 - 10.1079/PHN2002429

DO - 10.1079/PHN2002429

M3 - Article

VL - 6

SP - 313

EP - 321

JO - Public Health Nutrition

JF - Public Health Nutrition

SN - 1368-9800

IS - 3

ER -