A Simulation Study for Examining Roles of Sampling Weight in Multilevel Analysis with data from a Complex Survey Design

2021 ◽  
Vol 59 (7) ◽  
pp. 85-105
Author(s):  
Hyekyung Jung ◽  
In-Yong Park
Keyword(s):  
Multilevel Analysis ◽  
Simulation Study ◽  
Survey Design ◽  
Complex Survey ◽  
Complex Survey Design

scholarly journals Adherence to DASH Dietary Pattern Is Inversely Associated with Osteoarthritis in Americans (P18-012-19)

2019 ◽  
Vol 3 (Supplement_1) ◽  
Author(s):  
Ellen Francis ◽  
Karen Kemper ◽  
Joel Williams ◽  
Liwei Chen
Keyword(s):  
Dietary Pattern ◽  
Survey Design ◽  
Dietary Factors ◽  
Common Disease ◽  
Dash Score ◽  
Complex Survey ◽  
Logistic Regression Models ◽  
Funding Sources ◽  
Lower Likelihood ◽  
Complex Survey Design

Abstract Objectives Osteoarthritis (OA) is a common disease which significantly contributes to disability among older adults. Dietary factors are suggested to play a role in preventing OA, however, studies in this area spare. The objective of this study was to assess the association between adherence to the Dietary Approaches to Stop Hypertension (DASH) and OA in American adults. Methods This study included United States (US) adults (≥aged 20 years) who participated NHANES cycles 2007–2016. The Dietary Approaches to Stop Hypertension (DASH) score was calculated from nine food items with a higher DASH score indicating better adherence to the DASH dietary pattern. Multivariable logistic regression models adjusted for age, education, race/ethnicity, household income, smoking, alcohol consumption, and total energy intake were used to estimate the adjusted odds ratios (aOR) and 95% confidence intervals (CI) of DASH with OA. All analyses accounted for the complex survey design. Results Among the 17,349 participants included in this study, 9.05% reported OA. The DASH score was inversely associated with OA. The aOR (95% CI) were 1.00 (ref), 0.09 (0.70, 1.16), and 0.74 (0.58, 0.94) (Ptrend = 0.01) across the DASH score tertiles. When analyses were stratified by BMI categories (normal, overweight, obese) the magnitude of the association was stronger and remained significant only among obese participants (i.e., BMI ≥ 30 kg/m2). Among participants with an obese BMI, participants with a DASH score in the highest tertile compared to participants with a DASH score in the lowest tertile had a 17% lower likelihood of having OA (P = 0.009). Conclusions In a representative sample of American adults, higher adherence to the DASH dietary pattern was associated with lower likelihood of having OA and this association was particularly evident among obese individuals. Funding Sources N/A. Supporting Tables, Images and/or Graphs

scholarly journals The impact of complex survey design on prevalence estimates of intakes of food groups in the Australian National Children's Nutrition and Physical Activity Survey

2011 ◽  
Vol 15 (8) ◽  
pp. 1362-1372 ◽  
Author(s):  
Sandy Burden ◽  
Yasmine Probst ◽  
David Steel ◽  
Linda Tapsell
Keyword(s):  
Physical Activity ◽  
Survey Design ◽  
Food Groups ◽  
Sample Design ◽  
Complex Survey ◽  
Children's Nutrition ◽  
Prevalence Estimates ◽  
Complex Survey Design ◽  
Activity Survey ◽  
The Impact

AbstractObjectiveTo 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.DesignThe 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.SettingThe ANCNPAS07 used a complex sample design involving stratification, a high degree of clustering and estimation weights.SubjectsAustralian children aged 2–16 years.ResultsDesign 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.ConclusionsIgnoring 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.

scholarly journals Brazilians’ experiences with iron fortification: evidence of effectiveness for reducing inadequate iron intakes with fortified flour policy

2016 ◽  
Vol 20 (2) ◽  
pp. 363-370 ◽  
Author(s):  
Diva Aliete dos Santos Vieira ◽  
Josiane Steluti ◽  
Eliseu Verly-Jr ◽  
Dirce Maria Marchioni ◽  
Regina Mara Fisberg
Keyword(s):  
Survey Design ◽  
Age Groups ◽  
Substantial Reduction ◽  
Population Based ◽  
Reproductive Age ◽  
Cross Sectional ◽  
Complex Survey ◽  
Before And After ◽  
Complex Survey Design ◽  
Fortified Flour

AbstractObjectiveTo assess Fe intake, calculate the prevalence of inadequate Fe intake and identify food contributors to Fe intake during 2003 and 2008 in a population-based study, reflecting before and after the mandatory fortification of flour with Fe.DesignTwo cross-sectional population-based studies conducted in 2003 and 2008. Dietary intake was evaluated by 24 h recall and the Software for Intake Distribution Estimation (PC-SIDE) was used to estimate within-person variance and prevalence of inadequate Fe intake. The statistical analysis was conducted considering the complex survey design.SettingSão Paulo, Brazil.SubjectsAdolescents, adults and elderly adults of both sexes, interviewed in 2003 (n 2386) and 2008 (n 1661).ResultsThe Fe intake mean increased in all populations in the post-fortification period. A reduction of over 90 % was observed in the prevalence of inadequate Fe intake among men for all age groups analysed. When evaluating women, despite the substantial reduction (over 63 %), prevalence of inadequate Fe intake remained high (34 %) in those aged 19–50 years. Major food contributors to Fe intake before fortification were beans, beef, vegetables and dairy. There was an alteration in the contributors in the post-fortification period, with bread, beef, beans and biscuits as main contributors.ConclusionsThe mandatory fortification with Fe significantly furthered the reduction in the prevalence of inadequacy, except among women of reproductive age, and changed the main contributors to this nutrient in the studied population. Therefore, monitoring of Fe addition in flour is essential to assess compliance to the fortified flour policy and to guarantee a safe Fe intake for all the population.

scholarly journals Physical violence and violent threats reported by Aboriginal and Torres Strait Islander people with a disability: cross sectional evidence from a nationally representative survey

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Jeromey B. Temple ◽  
Heather Wong ◽  
Angeline Ferdinand ◽  
Scott Avery ◽  
Yin Paradies ◽  
...  
Keyword(s):  
Torres Strait Islander ◽  
Physical Violence ◽  
Survey Design ◽  
Exposure To Violence ◽  
Royal Commission ◽  
Torres Strait Islander People ◽  
Cross Sectional ◽  
Complex Survey ◽  
Complex Survey Design ◽  
Torres Strait

Abstract Background A recent Royal Commission into the treatment of Australians living with disabilities has underscored the considerable exposure to violence and harm in this population. Yet, little is known about exposure to violence among Aboriginal and Torres Strait Islander people living with disabilities. The objective of this paper was to examine the prevalence, disability correlates and aspects of violence and threats reported by Aboriginal and Torres Strait Islander people living with disabilities. Methods Data from the 2014–15 National Aboriginal and Torres Strait Islander Social Survey were used to measure physical violence, violent threats and disability. Multivariable logistic and ordinal logistic regression models adjusted for complex survey design were used to examine the association between measures of disability and exposure to violence and violent threats. Results In 2014–15, 17% of Aboriginal and Torres Strait Islander people aged 15–64 with disability experienced an instance of physical violence compared with 13% of those with no disability. Approximately 22% of those with a profound or severe disability reported experiencing the threat of physical violence. After adjusting for a comprehensive set of confounding factors and accounting for complex survey design, presence of a disability was associated with a 1.5 odds increase in exposure to physical violence (OR = 1.54 p < 0.001), violence with harm (OR = 1.55 p < 0.001), more frequent experience of violence (OR = 1.55 p < 0.001) and a 2.1 odds increase (OR = 2.13 p < 0.001) in exposure to violent threats. Severity of disability, higher numbers of disabling conditions as well as specific disability types (e.g., psychological or intellectual) were associated with increased odds of both physical violence and threats beyond this level. Independent of these effects, removal from one’s natural family was strongly associated with experiences of physical violence and violent threats. Aboriginal and Torres Strait Islander women, regardless of disability status, were more likely to report partner or family violence, whereas men were more likely to report violence from other known individuals. Conclusion Aboriginal and Torres Strait Islander people with disability are at heightened risk of physical violence and threats compared to Aboriginal and Torres Strait Islander people without disability, with increased exposure for people with multiple, severe or specific disabilities.

scholarly journals The Association between Stressful Events and Food Insecurity: Cross-Sectional Evidence from Australia

2018 ◽  
Vol 15 (11) ◽  
pp. 2333 ◽  
Author(s):  
Jeromey Temple
Keyword(s):  
Food Insecurity ◽  
Stressful Life Events ◽  
Survey Design ◽  
General Social Survey ◽  
Stressful Events ◽  
Economic Policies ◽  
Cross Sectional ◽  
Complex Survey ◽  
Complex Survey Design ◽  
Nationally Representative

A considerable body of empirical evidence exists on the demographic and socio-economic correlates of food insecurity in Australia. An important omission from recent studies, however, is an understanding of the role of stressful life events, or stressors in explaining exposure to food insecurity. Using nationally representative data from the 2014 General Social Survey and multivariable logistic regression, this paper reports on the association between 18 discrete stressors and the likelihood of reporting food insecurity in Australia. The results, adjusted for known correlates of food insecurity and complex survey design, show that exposure to stressors significantly increased the likelihood of experiencing food insecurity. Importantly, stressors related to employment and health approximately doubled the odds of experiencing food insecurity. The results underscore the complex correlates of food insecurity and indicates that conceptually it interacts with many important social and economic problems in contemporary Australia. There is no simple fix to food insecurity and solutions require co-ordination across a range of social and economic policies.

scholarly journals Modeling excess zeros and heterogeneity in count data from a complex survey design with application to the demographic health survey in sub-Saharan Africa

2016 ◽  
Vol 27 (1) ◽  
pp. 208-220 ◽  
Author(s):  
Lin Dai ◽  
Michael D Sweat ◽  
Mulugeta Gebregziabher
Keyword(s):  
Count Data ◽  
Regional Variation ◽  
Rate Ratio ◽  
Negative Binomial ◽  
Survey Design ◽  
Negative Binomial Model ◽  
Binomial Model ◽  
Complex Survey ◽  
Excess Zeros ◽  
Complex Survey Design

Purpose To show a novel application of a weighted zero-inflated negative binomial model in modeling count data with excess zeros and heterogeneity to quantify the regional variation in HIV-AIDS prevalence in sub-Saharan African countries. Methods Data come from latest round of the Demographic and Health Survey (DHS) conducted in three countries (Ethiopia-2011, Kenya-2009 and Rwanda-2010) using a two-stage cluster sampling design. The outcome is an aggregate count of HIV cases in each census enumeration area of each country. The outcome data are characterized by excess zeros and heterogeneity due to clustering. We compare scale weighted zero-inflated negative binomial models with and without random effects to account for zero-inflation, complex survey design and clustering. Finally, we provide marginalized rate ratio estimates from the best zero-inflated negative binomial model. Results The best fitting zero-inflated negative binomial model is scale weighted and with a common random intercept for the three countries. Rate ratio estimates from the final model show that HIV prevalence is associated with age and gender distribution, HIV acceptance, HIV knowledge, and its regional variation is associated with divorce rate, burden of sexually transmitted diseases and rural residence. Conclusions Scale weighted zero-inflated negative binomial with proper modeling of random effects is shown to be the best model for count data from a complex survey design characterized by excess zeros and extra heterogeneity. In our data example, the final rate ratio estimates show significant regional variation in the factors associated with HIV prevalence indicating that HIV intervention strategies should be tailored to the unique factors found in each country.

Estimation from an Under-Covered Sample in a Complex Survey for Auditing

2003 ◽  
Vol 54 (1-2) ◽  
pp. 115-120 ◽  
Author(s):  
Arijit Chaudhuri
Keyword(s):  
Survey Design ◽  
Simple Random Sampling ◽  
Complex Survey ◽  
Population Total ◽  
Government Documents ◽  
Complex Survey Design ◽  
The Mean ◽  
Mean Square Errors ◽  
Implementation Stage ◽  
Selection Of

We encounter a practical problem when from a finite population a complex survey design justifies selection of a sample in five stages. The design stipulates selecting a specified number of n(> 2) first stage units by Rao, Hartley and Cochran's (RHC, 1962) scheme followed by simple random sampling (SRS) without replacement (WOR) in each of the four subsequent stages. At the implementation stage a resource crunch calls for reducing the first stage sample size from n to m ( m < n). The consequential modifications in the methods of estimation of population total, mean and ratio of two totals and those of the variance of the first and the mean square errors of the latter two estimators are spelt out. The problem arises in the context of designing audits of Government documents by appropriate sampling.

scholarly journals Survey design and analysis considerations when utilizing misclassified sampling strata

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Aya A. Mitani ◽  
Nathaniel D. Mercaldo ◽  
Sebastien Haneuse ◽  
Jonathan S. Schildcrout
Keyword(s):  
Ethnic Minorities ◽  
Random Sampling ◽  
Survey Design ◽  
Simple Random Sampling ◽  
Stratified Sampling ◽  
Simple Random Sample ◽  
Parameter Estimates ◽  
Complex Survey ◽  
Racial And Ethnic Minorities ◽  
Complex Survey Design

Abstract Background A large multi-center survey was conducted to understand patients’ perspectives on biobank study participation with particular focus on racial and ethnic minorities. In order to enrich the study sample with racial and ethnic minorities, disproportionate stratified sampling was implemented with strata defined by electronic health records (EHR) that are known to be inaccurate. We investigate the effect of sampling strata misclassification in complex survey design. Methods Under non-differential and differential misclassification in the sampling strata, we compare the validity and precision of three simple and common analysis approaches for settings in which the primary exposure is used to define the sampling strata. We also compare the precision gains/losses observed from using a disproportionate stratified sampling scheme compared to using a simple random sample under varying degrees of strata misclassification. Results Disproportionate stratified sampling can result in more efficient parameter estimates of the rare subgroups (race/ethnic minorities) in the sampling strata compared to simple random sampling. When sampling strata misclassification is non-differential with respect to the outcome, a design-agnostic analysis was preferred over model-based and design-based analyses. All methods yielded unbiased parameter estimates but standard error estimates were lowest from the design-agnostic analysis. However, when misclassification is differential, only the design-based method produced valid parameter estimates of the variables included in the sampling strata. Conclusions In complex survey design, when the interest is in making inference on rare subgroups, we recommend implementing disproportionate stratified sampling over simple random sampling even if the sampling strata are misclassified. If the misclassification is non-differential, we recommend a design-agnostic analysis. However, if the misclassification is differential, we recommend using design-based analyses.

Sign in / Sign up

Export Citation Format

Share Document