How to use replicate weights in health survey analysis using the National Nutrition and Physical Activity Survey as an example.

OBJECTIVE: 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. DESIGN: Descriptive statistics are computed and a logistic regression investigation of being overweight/obese is conducted using Stata. SETTING: Cross-sectional health survey with complex sample design where replicate weights are supplied rather than the variables containing sample design information. PARTICIPANTS: Responding adults from the National Nutrition and Physical Activity Survey (NNPAS) part of the Australian Health Survey (2011-2013). RESULTS: 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. CONCLUSIONS: Correct incorporation of the sampling weights and sample design is crucial for valid inference from survey data.

Alcohol and smoking consumption behaviours in older Australian adults: prevalence, period and socio-demographic differentials in the DYNOPTA sample.

PURPOSE: Alcohol consumption and tobacco use are key risk factors for chronic disease and health burden across the adult lifespan. We estimate the prevalence of alcohol consumption and smoking by age and time period in adults from mid to old age. METHODS: Participants (n = 50,652) were drawn from the Dynamic Analyses to Optimise Ageing (DYNOPTA) project and were compared with Australian National Health Survey data. Alcohol and smoking consumption DYNOPTA data were weighted to the estimated resident population of the sampling frame for each contributing study according to age and sex distributions within major statistical regions. RESULTS: Comparisons in the rates of smoking and alcohol consumption between DYNOPTA and other national surveys were comparable. Males were more likely to be (RRR = 2.12) or have been smokers (RRR = 2.97), whilst females were more likely to be non-drinkers (RRR = 2.52). Period effects were also identified; higher prevalence rates in consumption of alcohol (RRR = 3.21) and smoking (RRR = 1.67) for those contributing studies from the early 1990's, in comparison with those studies from the latter half of the decade, were reported. CONCLUSIONS: Over a decade, prevalence rates for high-risk consumption of alcohol and current smoking behaviour declined and suggest the possible impact of government health policy, with targeted-health policies, that included bans on public smoking, and a toughening of legislation against alcohol-related crime.

Information Based Diagnostic for Genetic Variance Parameter Estimation in Multi-Environment Trials.

Plant breeding programs evaluate varieties in series of field trials across years and locations, referred to as multi-environment trials (METs). These are an essential part of variety evaluation with the key aim of the statistical analysis of these datasets to accurately estimate the variety by environment (VE) effects. It has previously been thought that the number of varieties in common between environments, referred to as "variety connectivity," was a key driver of the reliability of genetic variance parameter estimation and that this in turn affected the reliability of predictions of VE effects. In this paper we have provided the link between the objectives of this work and those in model-based experimental design. We propose the use of the D -optimality criterion as a diagnostic to capture the information available for the residual maximum likelihood (REML) estimation of the genetic variance parameters. We demonstrate the methods for a dataset with pedigree information as well as evaluating the performance of the diagnostic using two simulation studies. This measure is shown to provide a superior diagnostic to the traditional connectivity type measure in the sense of better forecasting the uncertainty of genetic variance parameter estimates.

Estimates of probable dementia prevalence from population-based surveys compared with dementia prevalence estimates based on meta-analyses.

BACKGROUND: National data on dementia prevalence are not always available, yet it may be possible to obtain estimates from large surveys that include dementia screening instruments. In Australia, many of the dementia prevalence estimates are based on European data collected between 15 and 50 years ago. We derived population-based estimates of probable dementia and possible cognitive impairment in Australian studies using the Mini-Mental State Examination (MMSE), and compared these to estimates of dementia prevalence from meta-analyses of European studies. METHODS: Data sources included a pooled dataset of Australian longitudinal studies (DYNOPTA), and two Australian Bureau of Statistics National Surveys of Mental Health and Wellbeing. National rates of probable dementia (MMSE < 24) and possible cognitive impairment (24-26) were estimated using combined sample weights. RESULTS: Estimates of probable dementia were higher in surveys than in meta-analyses for ages 65-84, but were similar at ages 85 and older. Surveys used weights to account for sample bias, but no adjustments were made in meta-analyses. Results from DYNOPTA and meta-analyses had a very similar pattern of increase with age. Contrary to trends from some meta-analyses, rates of probable dementia were not higher among women in the Australian surveys. Lower education was associated with higher prevalence of probable dementia. Data from investigator-led longitudinal studies designed to assess cognitive decline appeared more reliable than government health surveys. CONCLUSIONS: This study shows that estimates of probable dementia based on MMSE in studies where cognitive decline and dementia are a focus, are a useful adjunct to clinical studies of dementia prevalence. Such information and may be used to inform projections of dementia prevalence and the concomitant burden of disease.

Prevalence of physical activity behaviour in older people: findings from the Dynamic Analyses to Optimise Ageing (DYNOPTA) project and Australian national survey data.

AIM: Many older people lead sedentary lives. National Health Survey physical activity prevalence data provide limited coverage of the 'old old' (≥75 years). METHOD: The Dynamic Analyses to Optimise Ageing (DYNOPTA) project's dataset provided physical activity data for 13,420 participants. Physical activity (walking, moderate- and vigorous-intensity activities in the previous week) was measured. Data were weighted and prevalence was calculated. RESULTS: The frequency of walking in DYNOPTA was similar to that in the national sample. Walking remained relatively stable until a decline among persons aged 80 years and over; moderate and vigorous activity declined in all but a minority of persons aged 70 years and over. Although DYNOPTA participants reported more physical activity than those in the contemporary national survey, the rates of sedentary behaviour were high. CONCLUSION: We require more information about the 'oldest old' (85+ years). There is great scope for increasing physical activity, even walking, among older people.

Indigenous Australians are under-represented in longitudinal ageing studies.

OBJECTIVE: Evidence-based policy depends on the availability of high-quality research that is relevant to the population. This study aimed to identify the available data on the health of older Indigenous Australians in population-based longitudinal studies of ageing. APPROACH: Evaluation of the Dynamic Analyses to Optimise Ageing Project (DYNOPTA) dataset that has pooled nine Australian longitudinal ageing studies, six of which were analysed here. MAIN OUTCOME MEASURES: Proportions of the DYNOPTA sample identified as Indigenous. RESULTS: Indigenous participants made up 0.7% of males and 0.5% of females in the weighted sample, compared with 0.8% of both sexes in the Australian population. Indigenous under-representation is greater at ages 45-54 than at older ages, despite overall greater participation in this age range. CONCLUSIONS AND IMPLICATIONS: Within the existing Australian longitudinal ageing studies, Indigenous Australians are under-represented. This means there is a significant gap in the evidence base relating to the health of older Indigenous Australians. Research approaches specifically designed to address the health and wellbeing of older Indigenous Australians are urgently required.

Understanding ageing in older Australians: the contribution of the Dynamic Analyses to Optimise Ageing (DYNOPTA) project to the evidence base and policy.

AIM: To describe the Dynamic Analyses to Optimise Ageing (DYNOPTA) project and illustrate its contributions to understanding ageing through innovative methodology, and investigations on outcomes based on the project themes. DYNOPTA provides a platform and technical expertise that may be used to combine other national and international datasets. METHODS: The DYNOPTA project has pooled and harmonised data from nine Australian longitudinal studies to create the largest available longitudinal dataset (n= 50652) on ageing in Australia. RESULTS: A range of findings have resulted from the study to date, including methodological advances, prevalence rates of disease and disability, and mapping trajectories of ageing with and without increasing morbidity. DYNOPTA also forms the basis of a microsimulation model that will provide projections of future costs of disease and disability for the baby boomer cohort. CONCLUSION: DYNOPTA contributes significantly to the Australian evidence base on ageing to inform key social and health policy domains.