Is it necessary to correct for measurement error in nutritional epidemiology?
Explore the source record for details and available documents.
Alcohol Drinking↗
Biomedical subjects
Laurence S Freedman
Publications and source records attributed to Laurence S Freedman.
A comparison of two dietary instruments for evaluating the fat-breast cancer relationship.
BACKGROUND: Previous research suggests food diaries may be more efficient than food frequency questionnaires (FFQ) in detecting a dietary fat-breast cancer relationship. We assessed this further using 4 day food records (FRs) and FFQs in a large sample. METHODS: Participants were from the non-intervention group of the dietary modification component of the Women's Health Initiative Clinical Trial: 603 breast cancer cases and 1206 controls matched on age, clinic, and length of follow-up. Relative risks (RRs) were estimated using unconditional logistic regression, adjusted for confounders and for the selection into the trial of women with an FFQ report exceeding 32% calories from fat. Direct comparison of the statistical power of the two instruments used the standardized log RR. An alternative analysis after removing subjects with missing covariate data was also conducted. RESULTS: The RR estimate for breast cancer in the top quintile of total fat intake, adjusted for confounders and total energy, was 1.82 (P for trend 0.02) for the FR but 0.67 for the FFQ (P for trend 0.24). Following adjustment for selection, estimates were 2.09 (P for trend 0.008) for the FR (alternative: 2.54, P for trend 0.006) and 1.71 (P for trend 0.18) for the FFQ (alternative: 1.24, P for trend 0.41). Similar results were seen for fat subtypes, particularly unsaturated fats. Comparisons showed higher statistical power for the FR than the FFQ (e.g. total fat, P = 0.08: alternative P = 0.01). CONCLUSIONS: Alternative instruments, such as FRs, may be preferable to FFQs for evaluating diet-disease relationships in cohort studies. The results support a positive association between dietary fat and breast cancer.
Aged↗
The food propensity questionnaire: concept, development, and validation for use as a covariate in a model to estimate usual food intake.
OBJECTIVE: Twenty-four-hour recalls capture rich information on food consumption, but suffer from inadequately measuring usual intakes of episodically consumed foods. We explore using food frequency questionnaire (FFQ) data as covariates in a statistical model to estimate individual usual intakes of episodically consumed foods and their distributions and describe the development of the Food Propensity Questionnaire, an FFQ introduced in the 2003-2004 National Health and Nutrition Examination Survey. DESIGN: We analyzed data from 965 adult participants in the Eating at America's Table Study who completed four 24-hour recalls and an FFQ. We assessed whether or not increasing FFQ-reported frequency was associated with both number of 24-hour recall consumption days and amounts reported. RESULTS: For 52 of 56 food groups (93%), and 218 of 230 individual foods (95%), there were significant monotonically increasing relationships between FFQ frequency and 24-hour recall probability of consumption. For 47 of 56 food groups (84%) and 55 of 230 (24%) individual foods, there were significant positive correlations between FFQ frequencies and consumption-day mean intake. CONCLUSIONS: We found strong and consistent relationships between reported FFQ frequency of food and food-group consumption and probability of consumption on 24-hour recalls. This supports the premise that frequency data may offer important covariate information in supplementing multiple recalls for estimating usual intake of food groups.
Adolescent↗
A new statistical method for estimating the usual intake of episodically consumed foods with application to their distribution.
OBJECTIVE: We propose a new statistical method that uses information from two 24-hour recalls to estimate usual intake of episodically consumed foods. STATISTICAL ANALYSES PERFORMED: The method developed at the National Cancer Institute (NCI) accommodates the large number of nonconsumption days that occur with foods by separating the probability of consumption from the consumption-day amount, using a two-part model. Covariates, such as sex, age, race, or information from a food frequency questionnaire, may supplement the information from two or more 24-hour recalls using correlated mixed model regression. The model allows for correlation between the probability of consuming a food on a single day and the consumption-day amount. Percentiles of the distribution of usual intake are computed from the estimated model parameters. RESULTS: The Eating at America's Table Study data are used to illustrate the method to estimate the distribution of usual intake for whole grains and dark-green vegetables for men and women and the distribution of usual intakes of whole grains by educational level among men. A simulation study indicates that the NCI method leads to substantial improvement over existing methods for estimating the distribution of usual intake of foods. CONCLUSIONS: The NCI method provides distinct advantages over previously proposed methods by accounting for the correlation between probability of consumption and amount consumed and by incorporating covariate information. Researchers interested in estimating the distribution of usual intakes of foods for a population or subpopulation are advised to work with a statistician and incorporate the NCI method in analyses.
Analysis of Variance↗
Statistical methods for estimating usual intake of nutrients and foods: a review of the theory.
Although 24-hour recalls are frequently used in dietary assessment, intake on a single day is a poor estimator of long-term usual intake. Statistical modeling mitigates this limitation more effectively than averaging multiple 24-hour recalls per respondent. In this article, we describe the statistical theory that underlies the four major modeling methods developed to date, then review the strengths and limitations of each method. We focus on the problem of estimating the distribution of usual intake for a population from 24-hour recall data, giving special attention to the problems inherent in modeling usual intake for foods or food groups that a proportion of the population does not consume every day (ie, episodically consumed foods). All four statistical methods share a common framework. Differences between the methods arise from different assumptions about the measurement characteristics of 24-hour recalls and from the fact that more recently developed methods build upon their predecessor(s). These differences can result in estimated usual intake distributions that differ from one another. We also demonstrate the need for an improved method for estimating usual intake distributions for episodically consumed foods.
Data Interpretation, Statistical↗
Dietary intake changes and their association with ovarian cancer risk.
There are reasons to suspect that dietary changes through adult life may modify risk for some cancers. We examined the association of recent and past dietary habits and changes in dietary intake over time with ovarian cancer risk. Long-term nutritional assessment was performed retrospectively in 631 incident cases of invasive epithelial ovarian cancer and in 1174 matched controls (matched by age +/- 2 y, country of origin, and period of immigration) as part of a nationwide case-control study of ovarian cancer conducted between the years of 1994 and 1996 in Israel. Using a 2-step quantified Food Frequency Questionnaire, participants were first asked about their consumption of food items 1 y prior to the interview, and then whether their consumption had changed over time. The time of the change and consumption level before the change were recorded, allowing reconstruction of daily intakes for several time points. The reported mean percentage of animal fat intake decreased by 1.3% in cases but by 1.9% in controls (P for difference = 0.003). Conditional multivariate logistic regression was used to estimate odds ratios adjusted for total energy, parity, and oral contraceptive use. Substituting nonanimal fat in preference to animal fat over a relatively short term (between 2 and 7 y prior to interview) decreased the risk of ovarian cancer [OR = 0.65/100 kcal (418.4 kJ), 95% CI = 0.50 - 0.85]. Our results suggest that substitution of nonanimal for animal fat during adult life might reduce the risk of ovarian cancer, but this requires confirmation in prospective studies.
Adult↗
Seemingly unrelated measurement error models, with application to nutritional epidemiology.
Motivated by an important biomarker study in nutritional epidemiology, we consider the combination of the linear mixed measurement error model and the linear seemingly unrelated regression model, hence Seemingly Unrelated Measurement Error Models. In our context, we have data on protein intake and energy (caloric) intake from both a food frequency questionnaire (FFQ) and a biomarker, and wish to understand the measurement error properties of the FFQ for each nutrient. Our idea is to develop separate marginal mixed measurement error models for each nutrient, and then combine them into a larger multivariate measurement error model: the two measurement error models are seemingly unrelated because they concern different nutrients, but aspects of each model are highly correlated. As in any seemingly unrelated regression context, the hope is to achieve gains in statistical efficiency compared to fitting each model separately. We show that if we employ a "full" model (fully parameterized), the combination of the two measurement error models leads to no gain over considering each model separately. However, there is also a scientifically motivated "reduced" model that sets certain parameters in the "full" model equal to zero, and for which the combination of the two measurement error models leads to considerable gain over considering each model separately, e.g., 40% decrease in standard errors. We use the Akaike information criterion to distinguish between the two possibilities, and show that the resulting estimates achieve major gains in efficiency. We also describe theoretical and serious practical problems with the Bayes information criterion in this context.
Bias↗
Simple adjustments for randomized trials with nonrandomly missing or censored outcomes arising from informative covariates.
In randomized trials with missing or censored outcomes, standard maximum likelihood estimates of the effect of intervention on outcome are based on the assumption that the missing-data mechanism is ignorable. This assumption is violated if there is an unobserved baseline covariate that is informative, namely a baseline covariate associated with both outcome and the probability that the outcome is missing or censored. Incorporating informative covariates in the analysis has the desirable result of ameliorating the violation of this assumption. Although this idea of including informative covariates is recognized in the statistics literature, it is not appreciated in the literature on randomized trials. Moreover, to our knowledge, there has been no discussion on how to incorporate informative covariates into a general likelihood-based analysis with partially missing outcomes to estimate the quantities of interest. Our contribution is a simple likelihood-based approach for using informative covariates to estimate the effect of intervention on a partially missing outcome in a randomized trial. The first step is to create a propensity-to-be-missing score for each randomization group and divide the scores into a small number of strata based on quantiles. The second step is to compute stratum-specific estimates of outcome derived from a likelihood-analysis conditional on the informative covariates, so that the missing-data mechanism is ignorable. The third step is to average the stratum-specific estimates and compute the estimated effect of intervention on outcome. We discuss the computations for univariate, survival, and longitudinal outcomes, and present an application involving a randomized study of dual versus triple combinations of HIV-1 reverse transcriptase inhibitors.
Acquired Immunodeficiency Syndrome↗
Adjustments to improve the estimation of usual dietary intake distributions in the population.
We reexamined the current practice in estimating the distribution of usual dietary nutrient intakes from population surveys when using self-report dietary instruments, particularly the 24-h recall (24HR), in light of the new data from the Observing Protein and Energy Nutrition Study. In this study, reference biomarkers for energy (doubly labeled water) and protein [urinary nitrogen (UN)], together with multiple FFQs and 24HRs, were administered to 484 healthy volunteers. By using the reference biomarkers to estimate the distributions for energy and protein, the data confirmed previous reports that FFQs generally do not give an accurate impression of the distribution of usual dietary intake. The traditional method applied to 24HRs performed poorly because of underestimating the mean and overestimating the SD of the usual energy and protein intake distributions, and, although the National Research Council and the Iowa State University methods generally give better estimates of the shape of the distribution, they did not improve the estimates of the mean (10-15% underestimation for energy and 6-7% underestimation for protein). Results for urinary potassium, a putative biomarker for potassium intake, and reported potassium intake did not display this underestimation and may reflect either differential underreporting of foods or inadequacy of the potassium biomarker. A large controlled feeding study is required to validate conclusively the potassium biomarker. For energy intake, adjusting its 24HR-based distribution by using the UN biomarker appeared to capture the usual intake distribution quite accurately. Incorporating UN assessments into nutritional surveys, therefore, deserves serious consideration.
Adult↗
A new method for dealing with measurement error in explanatory variables of regression models.
We introduce a new method, moment reconstruction, of correcting for measurement error in covariates in regression models. The central idea is similar to regression calibration in that the values of the covariates that are measured with error are replaced by "adjusted" values. In regression calibration the adjusted value is the expectation of the true value conditional on the measured value. In moment reconstruction the adjusted value is the variance-preserving empirical Bayes estimate of the true value conditional on the outcome variable. The adjusted values thereby have the same first two moments and the same covariance with the outcome variable as the unobserved "true" covariate values. We show that moment reconstruction is equivalent to regression calibration in the case of linear regression, but leads to different results for logistic regression. For case-control studies with logistic regression and covariates that are normally distributed within cases and controls, we show that the resulting estimates of the regression coefficients are consistent. In simulations we demonstrate that for logistic regression, moment reconstruction carries less bias than regression calibration, and for case-control studies is superior in mean-square error to the standard regression calibration approach. Finally, we give an example of the use of moment reconstruction in linear discriminant analysis and a nonstandard problem where we wish to adjust a classification tree for measurement error in the explanatory variables.
Bayes Theorem↗
Structure of dietary measurement error: results of the OPEN biomarker study.
Multiple-day food records or 24-hour dietary recalls (24HRs) are commonly used as "reference" instruments to calibrate food frequency questionnaires (FFQs) and to adjust findings from nutritional epidemiologic studies for measurement error. Correct adjustment requires that the errors in the adopted reference instrument be independent of those in the FFQ and of true intake. The authors report data from the Observing Protein and Energy Nutrition (OPEN) Study, conducted from September 1999 to March 2000, in which valid reference biomarkers for energy (doubly labeled water) and protein (urinary nitrogen), together with a FFQ and 24HR, were observed in 484 healthy volunteers from Montgomery County, Maryland. Accounting for the reference biomarkers, the data suggest that the FFQ leads to severe attenuation in estimated disease relative risks for absolute protein or energy intake (a true relative risk of 2 would appear as 1.1 or smaller). For protein adjusted for energy intake by using either nutrient density or nutrient residuals, the attenuation is less severe (a relative risk of 2 would appear as approximately 1.3), lending weight to the use of energy adjustment. Using the 24HR as a reference instrument can seriously underestimate true attenuation (up to 60% for energy-adjusted protein). Results suggest that the interpretation of findings from FFQ-based epidemiologic studies of diet-disease associations needs to be reevaluated.
Adult↗
A simple method for analyzing data from a randomized trial with a missing binary outcome.
BACKGROUND: Many randomized trials involve missing binary outcomes. Although many previous adjustments for missing binary outcomes have been proposed, none of these makes explicit use of randomization to bound the bias when the data are not missing at random. METHODS: We propose a novel approach that uses the randomization distribution to compute the anticipated maximum bias when missing at random does not hold due to an unobserved binary covariate (implying that missingness depends on outcome and treatment group). The anticipated maximum bias equals the product of two factors: (a) the anticipated maximum bias if there were complete confounding of the unobserved covariate with treatment group among subjects with an observed outcome and (b) an upper bound factor that depends only on the fraction missing in each randomization group. If less than 15% of subjects are missing in each group, the upper bound factor is less than.18. RESULTS: We illustrated the methodology using data from the Polyp Prevention Trial. We anticipated a maximum bias under complete confounding of.25. With only 7% and 9% missing in each arm, the upper bound factor, after adjusting for age and sex, was.10. The anticipated maximum bias of.25 x.10 =.025 would not have affected the conclusion of no treatment effect. CONCLUSION: This approach is easy to implement and is particularly informative when less than 15% of subjects are missing in each arm.
Adenoma↗
A comparison of a food frequency questionnaire with a 24-hour recall for use in an epidemiological cohort study: results from the biomarker-based Observing Protein and Energy Nutrition (OPEN) study.
BACKGROUND: Most large cohort studies have used a food frequency questionnaire (FFQ) for assessing dietary intake. Several biomarker studies, however, have cast doubt on whether the FFQ has sufficient precision to allow detection of moderate but important diet-disease associations. We use data from the Observing Protein and Energy Nutrition (OPEN) study to compare the performance of a FFQ with that of a 24-hour recall (24HR). METHODS: The OPEN study included 484 healthy volunteer participants (261 men, 223 women) from Montgomery County, Maryland, aged 40-69. Each participant was asked to complete a FFQ and 24HR on two occasions 3 months apart, and a doubly labelled water (DLW) assessment and two 24-hour urine collections during the 2 weeks after the first FFQ and 24HR assessment. For both the FFQ and 24HR and for both men and women, we calculated attenuation factors for absolute energy, absolute protein, and protein density. RESULTS: For absolute energy and protein, a single FFQ's attenuation factor is 0.04-0.16. Repeat administrations lead to little improvement (0.08-0.19). Attenuation factors for a single 24HR are 0.10-0.20, but four repeats would yield attenuations of 0.20-0.37. For protein density a single FFQ has an attenuation of 0.3-0.4; for a single 24HR the attenuation factor is 0.15-0.25 but would increase to 0.35-0.50 with four repeats. CONCLUSIONS: Because of severe attenuation, the FFQ cannot be recommended as an instrument for evaluating relations between absolute intake of energy or protein and disease. Although this attenuation is lessened in analyses of energy-adjusted protein, it remains substantial for both FFQ and multiple 24HR. The utility of either of these instruments for detecting important but moderate relative risks (between 1.5 and 2.0), even for energy-adjusted dietary factors, is questionable.
Adult↗