To conduct nutrition-related analyses on large-scale health surveys, two aspects of the survey must be incorporated into the analysis: the sampling weights and the sample design; a practice which is not always observed. The present paper compares three analyses: (1) unweighted; (2) weighted but not accounting for the complex sample design; and (3) weighted and accounting for the complex design using replicate weights.

Descriptive statistics are computed and a logistic regression investigation of being overweight/obese is conducted using Stata.

Cross-sectional health survey with complex sample design where replicate weights are supplied rather than the variables containing sample design information.

Responding adults from the National Nutrition and Physical Activity Survey (NNPAS) part of the Australian Health Survey (2011–2013).

Unweighted analysis produces biased estimates and incorrect estimates of se. Adjusting for the sampling weights gives unbiased estimates but incorrect se estimates. Incorporating both the sampling weights and the sample design results in unbiased estimates and the correct se estimates. This can affect interpretation; for example, the incorrect estimate of the OR for being a current smoker in the unweighted analysis was 1·20 (95 % CI 1·06, 1·37), t= 2·89, P = 0·004, suggesting a statistically significant relationship with being overweight/obese. When the sampling weights and complex sample design are correctly incorporated, the results are no longer statistically significant: OR = 1·06 (95 % CI 0·89, 1·27), t = 0·71, P = 0·480.

Correct incorporation of the sampling weights and sample design is crucial for valid inference from survey data.

To assess the impact of the complex survey design used in the 2007 Australian National Children's Nutrition and Physical Activity Survey (ANCNPAS07) on prevalence estimates for intakes of groups of foods in the population of children.

The impacts on prevalence estimates were determined by calculating design effects for values for food group consumption. The implications of ignoring elements of the sample design including stratification, clustering and weighting are discussed.

The ANCNPAS07 used a complex sample design involving stratification, a high degree of clustering and estimation weights.

Australian children aged 2–16 years.

Design effects ranging from <1 to 5 were found for the values of mean consumption and proportion of the population consuming the food groups. When survey weights were ignored, prevalence estimates were also biased.

Ignoring the complex survey design used in the ANCNPAS07 could result in underestimating the width of confidence intervals, higher mean square errors and biased estimators. The magnitude of these effects depends on both the parameter under consideration and the chosen estimator.