Allowing for never and episodic consumers when correcting for error in food record measurements of dietary intake.  
Jump to Full Text  
MedLine Citation:

PMID: 21378386 Owner: NLM Status: MEDLINE 
Abstract/OtherAbstract:

Food records, including 24hour recalls and diet diaries, are considered to provide generally superior measures of longterm dietary intake relative to questionnairebased methods. Despite the expense of processing food records, they are increasingly used as the main dietary measurement in nutritional epidemiology, in particular in substudies nested within prospective cohorts. Food records are, however, subject to excess reports of zero intake. Measurement error is a serious problem in nutritional epidemiology because of the lack of gold standard measurements and results in biased estimated dietdisease associations. In this paper, a 3part measurement error model, which we call the never and episodic consumers (NEC) model, is outlined for food records. It allows for both real zeros, due to never consumers, and excess zeros, due to episodic consumers (EC). Repeated measurements are required for some study participants to fit the model. Simulation studies are used to compare the results from using the proposed model to correct for measurement error with the results from 3 alternative approaches: a crude approach using the mean of repeated food record measurements as the exposure, a linear regression calibration (RC) approach, and an EC model which does not allow real zeros. The crude approach results in badly attenuated odds ratio estimates, except in the unlikely situation in which a large number of repeat measurements is available for all participants. Where repeat measurements are available for all participants, the 3 correction methods perform equally well. However, when only a subset of the study population has repeat measurements, the NEC model appears to provide the best method for correcting for measurement error, with the 2 alternative correction methods, in particular the linear RC approach, resulting in greater bias and loss of coverage. The NEC model is extended to include adjustment for measurements from food frequency questionnaires, enabling better estimation of the proportion of never consumers when the number of repeat measurements is small. The methods are applied to 7day diary measurements of alcohol intake in the EPICNorfolk study. 
Authors:

Ruth H Keogh; Ian R White 
Related Documents
:

21549136  Feeding and reward: perspectives from three rat models of binge eating. 23532416  A rapid food screener ranks potential renal acid load of renal stone formers similarly ... 23322656  Does the analysis of the enantiomeric composition of clenbuterol in human urine enable ... 23378086  Malditof mass spectrometry for the monitoring of shedonkey's milk contamination or ad... 19064636  Human microbiotasecreted factors inhibit shiga toxin synthesis by enterohemorrhagic es... 14576176  The evolutionarily conserved gonadotropinreleasing hormone ii modifies food intake. 
Publication Detail:

Type: Comparative Study; Evaluation Studies; Journal Article; Research Support, NonU.S. Gov't Date: 20110304 
Journal Detail:

Title: Biostatistics (Oxford, England) Volume: 12 ISSN: 14684357 ISO Abbreviation: Biostatistics Publication Date: 2011 Oct 
Date Detail:

Created Date: 20110909 Completed Date: 20120116 Revised Date: 20140220 
Medline Journal Info:

Nlm Unique ID: 100897327 Medline TA: Biostatistics Country: England 
Other Details:

Languages: eng Pagination: 62436 Citation Subset: IM 
Export Citation:

APA/MLA Format Download EndNote Download BibTex 
MeSH Terms  
Descriptor/Qualifier:

Alcohol Drinking Bias (Epidemiology) Biostatistics Diet Records* Eating* Epidemiologic Methods Humans Linear Models Models, Statistical Odds Ratio Questionnaires 
Grant Support  
ID/Acronym/Agency:

MC_U105260558//Medical Research Council; MC_U105630924//Medical Research Council; U.1052.00.006//Medical Research Council 
Comments/Corrections 
Full Text  
Journal Information Journal ID (nlmta): Biostatistics Journal ID (hwp): biosts Journal ID (publisherid): biosts ISSN: 14654644 ISSN: 14684357 Publisher: Oxford University Press 
Article Information Download PDF © 2011 The Author(s) openaccess: Received Day: 25 Month: 6 Year: 2010 Revision Received Day: 02 Month: 12 Year: 2010 Accepted Day: 22 Month: 12 Year: 2010 Print publication date: Month: 10 Year: 2011 Electronic publication date: Day: 04 Month: 3 Year: 2011 pmcrelease publication date: Day: 04 Month: 3 Year: 2011 Volume: 12 Issue: 4 First Page: 624 Last Page: 636 ID: 3169666 PubMed Id: 21378386 DOI: 10.1093/biostatistics/kxq085 
Allowing for never and episodic consumers when correcting for error in food record measurements of dietary intake  
Ruth H. Keogh*  
Ian R. White  
MRC Biostatistics Unit, Robinson Way, Cambridge CB2 0SR, UK, MRC Centre for Nutritional Epidemiology in Cancer Prevention and Survival, Department of Public Health and Primary Care, University of Cambridge, Strangeways Research Laboratory, Worts Causeway Cambridge CB2 0SR, UK, ruth.keogh@mrcbsu.cam.ac.uk 

MRC Biostatistics Unit, Robinson Way, Cambridge CB2 0SR, UK 

*To whom correspondence should be addressed. 
In nutritional epidemiology, the exposure of interest is typically the longterm average daily intake of a nutrient, food, or food group (^{Willett, 1998}). The main method of assessing dietary intake in large prospective studies is the food frequency questionnaire (FFQ), on which participants report their habitual frequency of intake of a predefined list of food items, usually over the past year. FFQs are a relatively inexpensive measurement instrument but are subject to errors due to the difficulty of translating frequencies into absolute measures, omission of foods from the questionnaire, difficulty of recall, and personspecific errors (^{Willett, 1998}), (Kristal and others, 2005). Some large cohort studies have asked participants, often a subset of the study population, to provide more detailed information about dietary intake using food records (Bingham and others, 2001), (^{Riboli, 2001}), (Dahm and others, 2010), (Thompson and others, 2008). Food records include 24hour recalls, in which individuals recall intake on the previous day, and diet diaries, in which participants record intake over a few days (^{Willett, 1998}). Food records contain detailed portion size information and do not rely on longterm recall or restrict participants to a prespecified list of items.
Error in measures of dietary intake results in biased estimates of diet–disease associations (^{Willett, 1998}), (Carroll and others, 2006). The lack of any gold standard measurement for most nutrients and all foods means that it is difficult to assess the nature of error in dietary measurements. However, for the few nutrients for which a biomarker exists, food record measurements have been found to be more highly correlated with the objective biological measures than FFQ measurements (Kipnis and others, 2001), (Kipnis and others, 2002), (Kipnis and others, 2003), (Schatzkin and others, 2003), (Day and others, 2001). Food records are expensive to process and are not yet, to our knowledge, fully available in any large prospective cohort study. However, they are used as the main dietary measurement in case–control studies nested within cohorts, and some studies have observed statistically significant diet–disease associations using diet diaries but not FFQs (Bingham and others, 2003), (Dahm and others, 2010), (Freedman and others, 2006).
The shortterm nature of food records can result in excess reports of zero intake for foods which are not consumed on a daily or even weekly basis. These “episodically consumed” foods include alcohol, fish, and certain vegetables. However, there are also some foods which some people never consume or spend periods of many years without consuming. A measurement error modeling and correction procedure allowing for both never consumers and excess zeros has not been previously outlined in detail or compared with alternative approaches and these are the contributions of this paper.
Let T_{i} and R_{ij} denote true food intake and the food record measurement, respectively, for individual i on the jth measurement occasion. The diet–disease association is assumed linear on the appropriate scale for the outcome type, and β denotes the true association, for example, the log odds ratio (OR). Regression calibration (RC) estimates β by replacing T_{i} with E(T_{i}R_{ij}) in the diet–disease model (Carroll and others, 2006). The expectation E(T_{i}R_{ij}) is typically found by assuming a linear relationship between true and observed intake (Rosner and others, 1989): T_{i} = λ_{0} + λ_{1}R_{ij} + e_{i}. This model can be fitted provided an additional food record measurement is available for at least a subset of individuals, under the crucial assumption that food record measurements are subject only to random withinperson variability, that is, R_{ij} = T_{i} + ϵ_{ij}, where ϵ_{ij} is a random term with mean 0.
When food record measurements are subject to excess reports of zero intake, the linear association between T_{i} and R_{ij} no longer holds. Tooze and others (2006) developed a 2part model for error in 24hour recall measurements, with the aim of estimating the distribution of usual intake of episodically consumed foods in dietary surveillance studies. We refer to this as the episodic consumers (EC) model. A review of methods for estimating usual intake of episodically consumed foods is given by Dodd and others (2006). Kipnis and others (2009) extended the EC model for use in RC to correct for the effects of measurement error in 24hour recalls on diet–disease associations.
The EC model of Tooze and others (2006) and Kipnis and others (2009) makes the assumption that all individuals in the surveillance population or the epidemiologic cohort are consumers, to some degree, of the food in question. The first aim is to extend the EC model to accommodate never consumers. The resulting 3part model is called the never and episodic consumers (NEC) model and is outlined in Section 2. Kipnis and others (2009) suggested the extension of their model in this way in their discussion. In Section 3, the NEC model is fitted to 7day diet diary measurements of alcohol intake in the EPICNorfolk study. We use simulation studies in Section 4 to assess how well the NEC model can be fitted using different numbers of repeat measurements, how successful it is in allowing correction for measurement error in diet–disease association studies, and what advantages, if any, it offers over alternative approaches. In Section 5, we outline an extension of the NEC model to incorporate FFQ measurements. We conclude with a discussion in Section 6.
It is assumed that never consumers will never report nonzero intake, that is, Pr(R_{ij} = 0T_{i} = 0) = 1. We let H(γ_{0}) be the probability of being a consumer, where H(x) = exp(x)/(1 + exp(x)) and define a binary effect u_{0i} which indicates whether or not individual i is a consumer, such that
(2.1)
Conditionally on consumer status, the probability of reporting nonzero intake at time j is modeled as
(2.2)
Conditionally on reporting nonzero intake, the error in R_{ij} is modeled as
(2.3)
(2.4)
The NEC model defined by (2.1–2.3) can be fitted by maximum likelihood provided at least a subset of the population has repeat measurements. Suppose that the ith individual in the study population has J_{i} observed measurements and denote the set of measurements for individual i by R_{i} = {R_{i1},…,R_{iJi}}. For consumers, the joint conditional distribution of R_{i} given u_{i} is
(2.5)
where φ(·) denotes the probability density function for the standard normal distribution and I(R_{ij} > 0) is an indicator taking value 1 if R_{ij} > 0 and value 0 otherwise. It follows that the joint distribution of R_{i} given u_{i} is
(2.6)
The joint distribution of R_{i} is therefore
(2.7)
where f(u_{1i},u_{2i};θ) denotes the probability density function of the bivariate normal distribution for (u_{1i},u_{2i}). The full likelihood is L(θ) = ∏_{i}f(R_{i};θ).
To correct for measurement error using RC, we need to find the fitted values from the NEC model, . Using (2.4), we have
(2.8)
where f(u_{i};θ) is the joint distribution of u_{i}. The fitted values are estimated by first obtaining the maximum likelihood estimates for the model parameters, (Kipnis and others, 2009). Kipnis and others (2009) also allowed for a transformation g(T_{i}) to be used in the diet–disease model instead of T_{i} and (2.8) can be extended to calculate E(g(T_{i})R_{i};θ). The NEC model can be easily extended to include covariates in all 3 parts, giving conditional fitted values. For use in RC any covariates in the diet–disease model should be included.
Here, we extend the NEC model to allow the nonzero R_{ij} to be normally distributed on a transformed scale. This extension has been previously suggested by Tooze and others (2006) and Kipnis and others (2009) in their descriptions of the EC model. Suppose that there exists a Box–Cox transformation (^{Box and Cox, 1964}) g(x,λ) = (x^{λ} − 1)/λ, where λ = 0 indicates the log transformation, such that transformed measurements R_{ij}^{*} = g(R_{ij},λ) are normally distributed for R_{ij} > 0. The NEC model is now applied to the transformed measurements by replacing the first R_{ij} term in (2.3) by R_{ij}^{*}. For consumers, the joint conditional distribution of R_{i}^{*} = {R_{i1}^{*},…,R_{iJ}^{*}} given u_{i}, f(R_{i}^{*}u_{i},u_{0i} = 1;θ), is as in (2.5), but with R_{ij}^{*} in place of R_{ij} in the function φ(·) only. The unconditional joint distribution f(R_{i}^{*};θ) follows as before.
To calculate the fitted values, we maintain the assumption that the R_{ij} are unbiased for T_{i} on the untransformed scale, giving
(2.9)
Using a secondorder Taylor expansion, the expectation E(g^{ − 1}(R_{ij}^{*})u_{i},R_{ij} > 0;θ,λ) can be approximated by
(2.10)
The fitted values are
(2.11)
The nonzero R_{ij}^{*} in fact have a truncated normal distribution with R_{ij}^{*} ≥ − 1/λ because R_{ij} ≥ 0. Allowing R_{ij}^{*} < − 1/λ implies that γ_{2} + u_{2i} can be negative, presenting difficulties in the approximation in (2.10). In (2.11), therefore, it is appropriate to integrate over only the values of u_{2i} satisfying u_{2i} > − γ_{2} − 1/λ. Integrals in the likelihood and in calculation of fitted values have to be found numerically; we used Gauss–Hermite quadrature.
EPICNorfolk is a cohort of 25 639 individuals recruited during 1993–1997 from the population of individuals aged 45–75 years in Norfolk, UK (Day and others, 1999). During followup, study participants attended health checks at which dietary intake was assessed using 7day diet diaries and FFQs (Bingham and others, 2001). Many 7day diaries from 2 health checks have now been processed, from which measures of average daily alcohol intake (grams/day) are available. 17 971 individuals have at least one measurement and 2562 (15%) have 2. Of those with 2 measurements, 531 (21%) reported zero alcohol intake on both occasions, while 510 (21%) reported zero alcohol intake on one occasion only. Nonzero measurements of alcohol intake are approximately normally distributed after a Box–Cox transformation with λ = 0.25. The NEC model was fitted to the transformed 7day diary measurements of alcohol intake using all the data. Parameter estimates are shown in Table 1, and it is estimated that 12% of individuals are never consumers of alcohol.
We use a simulation study to investigate how well we can estimate the parameters of the NEC model using J repeat measurements for each individual, for values J = 2,4,10, and whether estimation of fitted values using the NEC model enables us to make successful corrections for measurement error in diet–disease association models. We use logistic models with true ORs of 1.2, 1.5, and 2. We also compare the corrected ORs found using the NEC model with those found using 3 alternative approaches: a crude analysis in which T_{i} is replaced by the mean of the observed measurements in the diet–disease model; replacing T_{i} with the fitted values from a linear RC model; and replacing T_{i} with the fitted values from the EC model. The EC model (Tooze and others, 2006), (, Kipnis:2009) is equivalent to parts (2.2) and (2.3) of the NEC model, under the assumption that u_{0i} = 1 for all i. Implementation of the crude and linear RC methods is outlined in Appendix A of the supplementary material available at Biostatistics online.
We base our simulation study on the results from fitting the NEC model to the EPICNorfolk 7day diary data on alcohol intake (Table 1). The proportion of never consumers is also increased to 25%. In practice, not all individuals in the study population will have repeat measurements, so we also investigate the case where 15% of the study population has J repeat measurements and the rest only have one.
Additional simulations were performed to further investigate the performance of the NEC model. The sample size for each simulated data set was increased from 1000 to 5000; we changed σ_{u1}^{2} to be larger and smaller than that in Table 1 (σ_{u1}^{2} = 2,8); and we increased σ_{ϵ}^{2} to 4. The effects on results of falsely assuming that the u_{1i} are normally distributed were investigated by repeating the simulations using heavy tailed and skew distributions for u_{1i}. Finally, we investigated the effect on results of misspecifying the Box–Cox transformation parameter λ. Full details of the simulation study are in Appendix B of the supplementary material available at Biostatistics online.
Table 2 shows the mean estimate of each NEC model parameter across 500 simulated data sets when H(γ_{0}) = 0.88 or 0.75 and when all or only a subset of individuals have J = 2,4,10 repeat measurements. Some parameter estimates are biased when the NEC model is fitted using 2 repeat measurements (J = 2), with H(γ_{0}) and σ_{u1}^{2} both biased upward. When J = 4, there is little bias in the parameter estimates, except for σ_{u1}^{2}, whose bias is substantially less than when J = 2. The empirical standard deviation of the estimates is lowered by increasing the number of repeats to J = 10, though there is little to be gained in terms of reducing bias, except in the estimation of σ_{u1}^{2}. When there is a higher proportion of never consumers, the bias in parameter estimates when J = 2 becomes more severe. When only 15% of individuals have a complete set of repeat measurements, a similar pattern of results is seen, with increased empirical standard deviations for parameter estimates.
Tables 1–3 in the supplementary material available at Biostatistics online show parameter estimates from the NEC model under the additional simulations. As σ_{u1}^{2} increases there is greater variability in the estimates, though the results are not strongly affected. When σ_{ϵ}^{2} increases there is also a small increase in the empirical standard deviations. A false assumption of normality of the random effects u_{1i} results in some bias in NEC parameter estimates, especially in σ_{u1}^{2} which is underestimated as J increases when the u_{1i} have a heavy tailed or skew distribution. The estimated proportion of consumers, H(γ_{0}), is slightly underestimated as J increases when the u_{1i} have a heavy tailed distribution but practically unaffected when the u_{1i} have a skew distribution. When λ is misspecified, the estimated proportion of consumers is more severely biased upward when there are a small number of repeats than when λ is correctly specified. All maximum likelihood estimations converged, with the exception of 3 simulations when the value of Box–Cox parameter λ was misspecified in the analysis using 2 repeats in the incomplete data situation.
Table 3 shows the mean, empirical standard deviation, and coverage of log OR estimates associated with a 10 grams/day increase in T_{i} found using fitted values from the NEC model, and under the 3 alternative approaches when H(γ_{0}) = 0.75. The corresponding results when H(γ_{0}) = 0.88 are shown in Table 4 of the supplementary material available at Biostatistics online. Log OR estimates found using the NEC model are subject to minor attenuation as the true log OR increases, which is alleviated as J increases. The attenuation is greater when only a subset of individuals have a complete set of repeat measurements. There is a corresponding slight loss of coverage in estimates. The crude approach results in attenuated log OR estimates, with the attenuation more severe as the true log OR increases and when fewer repeat measurements are used. There is a considerable loss of coverage when J = 2. This method performs particularly badly when only 15% of the study population has repeat measurements because the data are dominated by those with only one measurement.
Surprisingly, the linear RC correction for measurement error works well when all individuals in the study population have a complete set of repeat measurements. An explanation for this is outlined in Appendix C of the supplementary material available at Biostatistics online. However, in the more realistic situation in which only a subset of the study population has a complete set of repeat measurements, linear RC results in log OR estimates which are biased away from zero, resulting in a loss of coverage as the true log OR increases. The bias is only slightly moderated as the number of repeat measurements per person in the subset of the data with complete measurements increases. However, the bias is reduced when the sample size increases from 1000 to 5000 (Table 5, supplementary material available at Biostatistics online), though there is in fact a small decrease in coverage. Alongside the bias, standard errors for parameter estimates are underestimated under this method.
The EC model also gives estimates which are very close to those found under the NEC model when all individuals in the study population have repeat measurements. However, when only a subset of the study population has a complete set of repeat measurements, the EC model results in log OR estimates which have more conservative bias and there is greater loss of coverage as the true log OR increases.
Our additional analyses (Tables 6–8, supplementary materials available at Biostatistics online) show that σ_{u1}^{2} does not have a strong effect on the success of the measurement error correction. When σ_{ϵ}^{2} is large the bias in estimates is greater, there is greater loss of coverage under the NEC and EC models, and the crude method performs very badly. The comparisons between the methods are not materially altered by changes in these parameters. Results are also robust to departures from normality in the distribution of the u_{1i} and to misspecification of the Box–Cox parameter λ (Tables 9–11, supplementary material available at Biostatistics online).
Kipnis and others (2009) used FFQ measurements as a covariate in the EC model to improve the precision of parameter estimates. Here, we extend this to the NEC model. The lowest frequency of intake which can be reported on an FFQ is typically “never or less than once a month,” to which a measurement of zero is usually attributed. A comparison of FFQs from 2 time points in EPICNorfolk (11 824 individuals) found that 14% reported zero alcohol intake on both FFQs, while 10% reported zero intake on one but not the other. Of those 17 356 who completed both FFQ and 7day diary at the first health check, 17% reported zero intake on both, 14% reported zero intake on the diary but not the FFQ, and 4% reported zero intake on the FFQ but not the diary. In light of these observations, we consider it inappropriate to use FFQ measurements of zero as implying zero intake, but we do assume that a positive FFQ measurement implies a consumer.
Let denote the mean of the available FFQ measurements for individual i and denote the mean after an appropriate transformation, which takes value zero when all the FFQ measurements are zero. For generality, we let X_{i} denote a vector of other covariates. The FFQ and covariateadjusted NEC model is
(5.1)
(5.2)
(5.3)
FFQ measurements are assumed uncorrelated with ϵ_{ij}, and the random effects (u_{1i},u_{2i}) are independent of u_{0i} and have a bivariate normal distribution conditional on and X_{i}. Estimation of model parameters is via the conditional joint distribution , obtained as in Section (2.2).
To investigate the potential advantages of adjustment for FFQ measurements, we performed a simulation study in which data is generated according to the FFQadjusted model and then fitted with and without FFQadjustment. Full details are given in Appendix D of the supplementary material available at Biostatistics online. We compare the model parameter estimates and corrected ORs obtained using the unadjusted and FFQadjusted NEC model. The results are shown in Tables 4 and 5. When using J = 2 repeat measurements per individual, 8 out of 500 simulations failed to converge, and 2 out of 500 failed to converge when J = 4; these are omitted from the results below. There was also uncertainty as to whether 69 out of 492 of the remaining simulations fully converged when J = 2 and 29 out of 498 when J = 4 and 5 out of 500 when J = 10; in these cases it appears that all parameters were correctly estimated except for σ_{u1}^{2} for which the estimate was close to zero. In Table 4, we are primarily interested in the ability of the model to estimate the proportion of never consumers. With FFQadjustment the proportion of consumers is not overestimated when using only 2 repeat measurements per individual, as it is in the unadjusted model. The estimated ORs from the unadjusted and FFQadjusted models are similar (Table 5).
Until recently (Tooze and others, 2006), (, Kipnis:2009), there has been a gap in the statistical methodology for applying RC when there are zeros in the observed dietary measurements. This paper extends the earlier work to allow for a distinction between “real” zeros, due to never consumers, and excess zeros, which occur as a limitation of the dietary assessment instrument. We focused on use of the NEC model in nutritional epidemiological studies, where it is desirable to make corrections for measurement error. The model is relevant for the case–control studies nested within prospective cohorts which are beginning to use food records instead of FFQs as the main dietary measurement. In the future, some prospective studies will be able to perform full cohort analyses using food record measurements.
Our simulation studies showed that use of the NEC model, the EC model, or, unexpectedly, the standard linear RC model to make corrections for measurement error in diet–disease associations gives very similar results when all individuals in the study population have more than one food record measurement. Using only 2 repeat measurements results in underestimation of the proportion of never consumers in the NEC model. The greater the number of repeat measurements, the greater the ability of the model to distinguish never consumers from episodic consumers. The shorter the food record assessment period, the greater the problem of excess zeros will be.
Repeat measurements are usually available for only a small subset of the study population. In practice, therefore, the simulation study results relating to this situation are of most interest. In this case, the NEC model performed better than the alternative methods in terms of both bias and coverage of corrected estimated diet–disease associations. There is some conservative bias and modest loss of coverage in the estimates from the NEC model when the number of repeat measurements in the subset is small (e.g. 2) and as the size of the association gets large. The EC model has marginally greater conservative bias and greater loss of coverage, though the differences between the 2 approaches are fairly small. In this situation, using a linear RC model can result in biased estimated diet–disease associations in finite samples and large loss of coverage.
Additional information about dietary intake from FFQ measurements can be used to improve estimation of the proportion of consumers in an adjusted NEC model when the number of repeat measurements J is small because measurements of zero from the FFQ are very informative about whether an individual is a never consumer. The tradeoff is that FFQadjusted models may be more likely to fail to converge when J is small. Additional simulations (not shown) using covariateadjustment in all parts of the model suggest the same problem may occur and that estimates for parameters associated with being a never consumer may be unstable when J is small.
There is evidence that food record measurements can be subject to systematic error. We show in Appendix E of the supplementary material available at Biostatistics online, how this can be accommodated by the NEC model, though systematic errors would have to be investigated using sensitivity analyses. It is not clear that adjustment for FFQ in the NEC model allows for excess zeros in the FFQ measurements. Areas for further work include NEC models for both FFQs and food records with correlated random effects, and incorporation of biomarker measurements. An important extension will be to diet–disease models containing several dietary variables measured with error, one or more of which may be subject to excess zeros.
In summary, it is recommended that the NEC model be used to perform corrections for the effects of error in food record measurements where it is suspected that a substantial proportion of the study population may be never consumers, and when only a subset of the study population has repeat dietary measurements, using FFQ adjustment where possible. The EC model performs almost as well in many situations, and in some situations the standard linear RC method also performs well.
Supplementary material is available at http://biostatistics.oxfordjournals.org.
Medical Research Council (U.1052.00.006) to Ian White.
Click here for additional data file (supp_kxq085_keogh_biostats_supplementary_22062010_revised2.pdf)
Conflict of Interest: None declared.
References
Bingham SA,Luben R,Welch AA,Wareham N,Khaw KT,Day N. Are imprecise methods obscuring a relation between fat and breast cancer?The LancetYear: 2003362212214  
Bingham SA,Welch AA,McTaggart A,Mulligan AA,Runswick SA,Luben R,Oakes S,Khaw KT,Wareham N,Day NE. Nutritional methods in the European prospective investigation of cancer in NorfolkPublic Health NutritionYear: 2001484785811415493  
Box GEP,Cox DR. An analysis of transformationsJournal of the Royal Statistical Society, Series BYear: 196426211252  
Carroll RJ,Ruppert D,Stefanski LA,Crainiceanu CM. Measurement Error in Nonlinear Models: A Modern PerspectiveYear: 20062nd editionLondonChapman & Hall/CRC  
Dahm CC,Keogh RH,Spencer EA,Greenwood DC,Key TJ,Fentiman IS,Shipley MJ,Brunner EJ,Cade JE,Burley VJ,others. Dietary fiber and colorectal cancer risk: a nested casecontrol study using food diariesJournal of the National Cancer InstituteYear: 201010261462620407088  
Day NE,McKeown N,Wong MY,Welch A,Bingham S. Epidemiological assessment of diet: a comparison of a 7day diary with a food frequency questionnaire using urinary markers of nitrogen, potassium and sodiumInternational Journal of EpidemiologyYear: 20013030931711369735  
Day NE,Oakes S,Luben R,Khaw KT,Bingham S,Welch A,Wareham N. EPIC in Norfolk: study design and characteristics of the cohort. British Journal of Cancer 80SupplYear: 1999195103  
Dodd KW,Guenther PM,Freedman LS,Subar AF,Kipnis V,Midthune D,Tooze JA,KrebsSmith SM. Statistical methods for estimating usual intake of nutrients and foods: a review of the theoryJournal of the American Dietetic AssociationYear: 20061061640165017000197  
Freedman LS,Potischman N,Kipnis V,Midthune D,Schatzkin A,Thompson FE,Troiano RP,Prentice R,Patterson R,Carroll R. othersA comparison of two dietary instruments for evaluating the fatbreast cancer relationshipInternational Journal of EpidemiologyYear: 2006351011102116672309  
Kipnis V,Midthune D,Buckman DW,Dodd KW,Guentherm PM,KrebsSmith SM,Subar AF,Tooze JA,Carroll RJ,Freedman LS. Modeling data with excess zeros and measurement error: application to evaluating relationships between episodically consumed foods and health outcomesBiometricsYear: 2009651003101019302405  
Kipnis V,Midthune D,Freedman L,Bingham S,Day NE,Riboli E,Ferrari P,Carroll RJ. Bias in dietaryreporting instruments and its implications for nutritional epidemiologyPublic Health NutritionYear: 2002591592312633516  
Kipnis V,Midthune D,Freedman L,Bingham S,Schatzkin A,Subar A,Carroll RJ. Empirical evidence of correlated biases in dietary assessment instruments and its implicationsAmerican Journal of EpidemiologyYear: 200115339440311207158  
Kipnis V,Subar AF,Midthune D,Freedman LS,BallardBarbash R,Troiano RP,Bingham S,Schoeller DA,Schatzkin A,Carroll RJ. Structure of dietary measurement error: results of the OPEN biomarker studyAmerican Journal of EpidemiologyYear: 2003158142112835281  
Kristal AR,Peters U,Potter JD. Is it time to abandon the food frequency questionnaire?Cancer Epidemiology, Biomarkers and PreventionYear: 20051428262828  
Olsen MK,Schafer JL. A twopart randomeffects model for semicontinuous longitudinal dataJournal of the American Statistical AssociationYear: 200196730745  
Riboli E. The European prospective investigation into cancer and nutrition (EPIC): plans and progressJournal of NutritionYear: 2001131170S175S11208958  
Rosner B,Willett WC,Spiegelman D. Correction of logistic regression relative risk estimates and confidence intervals for systematic withinperson measurement errorStatistics in MedicineYear: 19898105110692799131  
Schatzkin A,Kipnis V,Carroll RJ,Midthune D,Subar AF,Bingham S,Schoeller DA,Troiano RP,Freedman LS. A comparison of a food frequency questionnaire with a 24hour recall for use in an epidemiological cohort study: results from the biomarkerbased observing protein and energy nutrition (OPEN) studyInternational Journal of EpidemiologyYear: 2003321054106214681273  
Thompson FE,Kipnis V,Midthune D,Freedman LS,Carroll RJ,Subar AF,Brown CC,Butcher MS,Mouw T,Leitzmann M,others. Performance of a foodfrequency questionnaire in the US NIHAARP (National Institutes of HealthAmerican Association of Retired Persons) diet and health studyPublic Health NutritionYear: 20081118319517610761  
Tooze JA,Midthune D,Dodd KW,Freedman LS,KrebsSmith SM,Subar AF,Guenther PM,Carroll RJ,Kipnis V. A new statistical method for estimating the usual intake of episodically consumed foods with application to their distributionJournal of the American Diebetic AssociationYear: 200610615751587  
Willett W. Nutritional EpidemiologyYear: 19982nd editionOxfordOxford University Press 
Tables
Parameter estimates (standard error [SE]) from fitting the NEC model using maximum likelihood to one or two 7day diary measurements of alcohol intake in EPICNorfolk
Parameter  Estimate (SE) 
γ_{1}  2.13 (0.09) 
γ_{2}  2.67 (0.06) 
σ_{u1}^{2}  4.13 (0.77) 
σ_{u2}^{2}  4.45 (0.15) 
ρ  0.91 (0.01) 
σ_{ϵ}^{2}  1.17 (0.04) 
H(γ_{0})  0.88 (0.02) 
Mean (empirical standard deviation) of maximum likelihood estimates of parameters from the NEC model across 500 simulated data sets using J = 2, 4, 10 repeat measurements, where 100% or 15% of individuals have a complete set of J measurements
Parameter  True value  Complete repeats

Incomplete repeats


J = 2  J = 4  J = 10  J = 2  J = 4  J = 10  
12% never consumers  
γ_{1}  2.13  2.01 (0.21)  2.14 (0.11)  2.13 (0.08)  2.07 (0.37)  2.16 (0.23)  2.15 (0.16) 
γ_{2}  2.67  2.51 (0.17)  2.67 (0.09)  2.67 (0.07)  2.54 (0.22)  2.67 (0.15)  2.69 (0.11) 
σ_{u1}^{2}  4.13  7.41 (3.11)  4.39 (0.75)  4.16 (0.38)  8.16 (4.88)  4.89 (2.27)  4.18 (0.93) 
σ_{u2}^{2}  4.45  4.72 (0.43)  4.45 (0.29)  4.44 (0.24)  4.65 (0.55)  4.43 (0.43)  4.39 (0.33) 
ρ  0.91  0.87 (0.03)  0.90 (0.02)  0.90 (0.01)  0.85 (0.03)  0.88 (0.05)  0.89 (0.03) 
σ_{ϵ}^{2}  1.17  1.17 (0.07)  1.17 (0.04)  1.16 (0.02)  1.16 (0.17)  1.16 (0.10)  1.17 (0.05) 
H(γ_{0})  0.88  0.94 (0.05)  0.88 (0.02)  0.88 (0.01)  0.93 (0.07)  0.88 (0.04)  0.87 (0.02) 
25% never consumers  
γ_{1}  2.13  1.85 (0.43)  2.13 (0.12)  2.13 (0.09)  1.81 (0.60)  2.14 (0.29)  2.15 (0.18) 
γ_{2}  2.67  2.43 (0.28)  2.66 (0.10)  2.67 (0.08)  2.42 (0.35)  2.66 (0.19)  2.68 (0.12) 
σ_{u1}^{2}  4.13  9.24 (6.12)  4.40 (0.84)  4.16 (0.41)  11.56 (9.69)  5.17 (3.27)  4.20 (1.03) 
σ_{u2}^{2}  4.45  4.85 (0.59)  4.46 (0.32)  4.45 (0.27)  4.85 (0.75)  4.46 (0.50)  4.40 (0.38) 
ρ  0.91  0.87 (0.03)  0.90 (0.02)  0.90 (0.01)  0.85 (0.05)  0.88 (0.04)  0.89 (0.02) 
σ_{ϵ}^{2}  1.17  1.17 (0.08)  1.17 (0.04)  1.17 (0.02)  1.16 (0.19)  1.17 (0.11)  1.17 (0.06) 
H(γ_{0})  0.75  0.83 (0.09)  0.75 (0.02)  0.75 (0.01)  0.85 (0.11)  0.76 (0.05)  0.75 (0.03) 
Mean (empirical standard deviation [SD]) of log OR estimates and coverage of 95% confidence intervals across 500 simulated data sets using different correction methods when there are J = 2, 4, 10 repeat measurements per person (for 100% or 15% of individuals) and 25% of individuals are {never consumers}
True β  Method


Using T_{i}  NEC model  Crude  Linear RC  EC model  
Complete repeats  
J = 2  
0.182  Mean (SD)  0.181 (0.070)  0.183 (0.076)  0.155 (0.065)  0.179 (0.075)  0.181 (0.076) 
Coverage  0.95  0.96  0.95  0.96  0.96  
0.405  Mean (SD)  0.409 (0.065)  0.411 (0.071)  0.349 (0.060)  0.404 (0.071)  0.406 (0.070) 
Coverage  0.93  0.93  0.78  0.92  0.93  
0.693  Mean (SD)  0.695 (0.065)  0.677 (0.069)  0.585 (0.060)  0.677 (0.070)  0.671 (0.068) 
Coverage  0.97  0.94  0.53  0.94  0.93  
J = 4  
0.182  Mean (SD)  0.181 (0.070)  0.182 (0.073)  0.167 (0.067)  0.180 (0.072)  0.179 (0.072) 
Coverage  0.95  0.95  0.96  0.95  0.95  
0.405  Mean (SD)  0.409 (0.065)  0.411 (0.066)  0.376 (0.061)  0.406 (0.066)  0.403 (0.065) 
Coverage  0.93  0.94  0.90  0.94  0.94  
0.693  Mean (SD)  0.695 (0.065)  0.687 (0.067)  0.635 (0.062)  0.685 (0.067)  0.675 (0.065) 
Coverage  0.97  0.96  0.85  0.95  0.94  
J = 10  
0.182  Mean (SD)  0.181 (0.070)  0.181 (0.070)  0.175 (0.068)  0.181 (0.070)  0.179 (0.069) 
Coverage  0.95  0.95  0.96  0.95  0.95  
0.405  Mean (SD)  0.409 (0.065)  0.409 (0.066)  0.395 (0.063)  0.407 (0.066)  0.403 (0.065) 
Coverage  0.93  0.93  0.92  0.93  0.93  
0.693  Mean (SD)  0.695 (0.065)  0.691 (0.066)  0.670 (0.064)  0.691 (0.066)  0.683 (0.065) 
Coverage  0.97  0.97  0.92  0.96  0.95  
Incomplete repeats  
J = 2  
0.182  Mean (SD)  0.181 (0.070)  0.185 (0.083)  0.138 (0.061)  0.195 (0.104)  0.184 (0.082) 
Coverage  0.95  0.96  0.94  0.91  0.96  
0.405  Mean (SD)  0.409 (0.065)  0.413 (0.076)  0.310 (0.055)  0.438 (0.144)  0.410 (0.075) 
Coverage  0.93  0.91  0.52  0.70  0.91  
0.693  Mean (SD)  0.695 (0.065)  0.669 (0.079)  0.517 (0.058)  0.728 (0.221)  0.666 (0.079) 
Coverage  0.97  0.89  0.16  0.52  0.88  
J = 4  
0.182  Mean (SD)  0.181 (0.070)  0.186 (0.083)  0.139 (0.062)  0.193 (0.100)  0.180 (0.080) 
Coverage  0.95  0.95  0.94  0.90  0.95  
0.405  Mean (SD)  0.409 (0.065)  0.415 (0.073)  0.312 (0.055)  0.433 (0.134)  0.402 (0.071) 
Coverage  0.93  0.93  0.55  0.72  0.92  
0.693  Mean (SD)  0.695 (0.065)  0.673 (0.074)  0.522 (0.058)  0.721 (0.203)  0.656 (0.072) 
Coverage  0.97  0.92  0.17  0.57  0.88  
J = 10  
0.182  Mean (SD)  0.181 (0.070)  0.186 (0.081)  0.140 (0.062)  0.191 (0.096)  0.177 (0.077) 
Coverage  0.95  0.96  0.94  0.90  0.96  
0.405  Mean (SD)  0.409 (0.065)  0.416 (0.073)  0.314 (0.056)  0.430 (0.130)  0.396 (0.069) 
Coverage  0.93  0.92  0.55  0.72  0.93  
0.693  Mean (SD)  0.695 (0.065)  0.675 (0.071)  0.525 (0.059)  0.714 (0.190)  0.647 (0.069) 
Coverage  0.97  0.93  0.17  0.60  0.87 
Mean (empirical standard deviation) of maximum likelihood estimates of parameters from the NEC model across 500 simulated data sets using J = 2,4,10 repeat measurements when the true proportion of never consumers is 87%: With and without FFQ adjustment
Parameter  Without FFQ adjustment

With FFQ adjustment


J = 2  J = 4  J = 10  J = 2  J = 4  J = 10  
γ_{1}  1.87 (0.19)  2.03 (0.10)  2.06 (0.08)  0.14 (0.09)  0.13 (0.06)  0.13 (0.04) 
γ_{2}  2.58 (0.14)  2.78 (0.08)  2.84 (0.07)  0.92 (0.08)  0.92 (0.06)  0.92 (0.05) 
σ_{u1}^{2}  7.19 (2.26)  3.67 (0.59)  3.17 (0.27)  0.14 (0.16)  0.07(0.06)  0.04 (0.02) 
σ_{u2}^{2}  4.17 (0.35)  3.79 (0.24)  3.66 (0.18)  0.61 (0.07)  0.61 (0.05)  0.61 (0.04) 
ρ  0.88 (0.03)  0.91 (0.01)  0.92 (0.01)  0.41 (0.50)  0.61 (0.32)  0.72 (0.19) 
σ_{ϵ}^{2}  1.28 (0.07)  1.28 (0.04)  1.28 (0.02)  1.28 (0.07)  1.28 (0.04)  1.28 (0.02) 
ξ_{1}        0.91 (0.06)  0.90 (0.04)  0.90 (0.02) 
ξ_{2}        0.88 (0.02)  0.88 (0.02)  0.88 (0.02) 
H(γ_{0})  0.96 (0.04)  0.88 (0.01)  0.88 (0.01)  0.38 (0.04)  0.37 (0.04)  0.37 (0.03) 
Proportion of consumers  0.96 (0.04)  0.88 (0.01)  0.88 (0.01)  0.87 (0.01)  0.87 (0.01)  0.87 (0.01) 
Mean (empirical standard deviation [SD]) of log OR estimates and coverage of 95% confidence intervals across 500 simulated data sets using the unadjusted and FFQadjusted NEC model when there are J = 2,4,10 repeat measurements per person
True β  Method


Using T_{i}  Without FFQ adjustment  With FFQ adjustment  
Complete repeats  
J = 2  
0.182  Mean (SD)  0.177 (0.076)  0.180 (0.084)  0.180 (0.081) 
Coverage  0.96  0.96  0.96  
0.405  Mean (SD)  0.410 (0.064)  0.410 (0.071)  0.413 (0.069) 
Coverage  0.95  0.94  0.94  
0.693  Mean (SD)  0.693 (0.067)  0.671 (0.072)  0.684 (0.070) 
Coverage  0.95  0.91  0.94  
J = 4  
0.182  Mean (SD)  0.177 (0.076)  0.180 (0.078)  0.180 (0.081) 
Coverage  0.96  0.97  0.96  
0.405  Mean (SD)  0.410 (0.064)  0.412 (0.068)  0.413 (0.069) 
Coverage  0.95  0.94  0.94  
0.693  Mean (SD)  0.693 (0.067)  0.684 (0.069)  0.684 (0.069) 
Coverage  0.95  0.95  0.95  
J = 10  
0.182  Mean (SD)  0.177 (0.076)  0.179 (0.077)  0.178 (0.077) 
Coverage  0.96  0.96  0.97  
0.405  Mean (SD)  0.410 (0.064)  0.413 (0.065)  0.412 (0.066) 
Coverage  0.95  0.95  0.94  
0.693  Mean (SD)  0.693 (0.067)  0.690 (0.068)  0.690 (0.068) 
Coverage  0.95  0.95  0.94 
Article Categories:
Keywords: Excess zeros, Measurement error, Nutritional epidemiology, Repeated measures. 
Previous Document: Enhanced contractility and myosin phosphorylation induced by Ca(2+)independent MLCK activity in hyp...
Next Document: Utility of cardiac biomarkers for the diagnosis of type V myocardial infarction after coronary arter...