ESRA logo
Tuesday 14th July      Wednesday 15th July      Thursday 16th July      Friday 17th July     

Tuesday 14th July, 14:00 - 15:30 Room: HT-102

Weighting issues in complex cross-sectional and longitudinal surveys 1

Convenor Ms Nicole Watson (University of Melbourne )
Coordinator 1Dr Olena Kaminska (University of Essex)

Session Details

A range of issues arise when constructing weights for surveys with complex designs. Use of mixed modes or multiple frames in cross-sectional, longitudinal or cross-national surveys may result in uncertainty in selection probabilities, fieldwork outcomes or response propensities that make it difficult to construct appropriate weights. Further, longitudinal surveys tend to have greater uncertainty over time (as interviews are no longer attempted with some people). Growing complexity of design for multi-purpose surveys calls for the development of weighting methods to reflect them.

How should weights be best constructed in the presence of uncertainty about inclusion probabilities or fieldwork outcomes? How should the response process be best modeled in cross-national surveys where countries differ in quality and type of sampling frame and other auxiliary data? For surveys with multiple frames, how do we best construct weights that combine samples from multiple sources that may have partial overlap in the presence of uncertainty about membership? In constructing weights for longitudinal samples, we need to consider how populations are defined over time, how to treat deaths and other out-of-scopes, how best to adjust for attrition. Further, in household-based longitudinal surveys we need to determine how to best incorporate new sample members arising from changes in the household structure.

This session seeks to bring together survey methodologists involved in constructing weights for complex surveys (both longitudinal and cross-sectional) to explore the approaches taken. Papers submitted to this session might include comparisons of alternative methods, analysis of the impact of a particular component of the weights, or suggestions for new methods.

Paper Details

1. An evaluation of alternative weightings for analysis of a complex cross-sectional health survey
Dr Robert Clark (University of Wollongong)

Regression analysis of survey data often incorporates the survey weights to allow for a complex sample design. Often the design weights are used for this purpose. Other possibilities include calibrated weights, the product of the design weights and a function of the covariates, smoothed weights given the values of the response and covariates, or unweighted approaches. The statistical and practical properties of these options are evaluated using the New Zealand Health Survey, which is an example of a complex, multi-stage, dual-frame health survey which oversamples ethnicities.

2. What is a representative genome? The challenges and benefits of applying complex survey weights to genome-wide data
Dr Colter Mitchell (University of Michigan)
Dr Steven Heeringa (University of Michigan)
Dr Roderick Little (University of Michigan)

Recent integration of representative survey data and genomewide data provides new opportunities to generate population health estimates. Currently, sampling weights are not applied to genomewide data and analyses. Using the New Solider Study, the Pre and Postdeployment Study (Army STARRS) and the Health and Retirement Study, we examine the effects of using sampling and non-response weights on generalizability in genomewide data analyses such Genome Wide Association Studies and Genomic Relatedness Matrix Restricted Maximum Likelihood. As biological data are often collected from separate consents and are sometime subsamples of the larger study, these weights are unique and challenging to create.

3. Weighting the European Social Survey: A comparison of effects on selected variables across countries and rounds
Ms Ana Slavec (University of Ljubljana)
Mr Vasja Vehovar (University of Ljubljana)

Data for all countries for 6 rounds were weighted and analysed. An inventory of 23 variables that appear in all rounds was used to compute non-response biases i.e. the differences between the weighted and the unweighted estimate. Absolute and relative, standardized and non-standardized biases were computed for the selected variables and compared to response rates. The results vary across countries - the larger the nonresponse rate, the higher are the biases. In addition, a sensibility analysis was performed to estimate variations in the weighting procedure.

4. Dead or Alive? Dealing with Unknown Eligibility in a Longitudinal Survey
Ms Nicole Watson (University of Melbourne)

Longitudinal surveys follow people over time and some deaths will occur during the life of the panel. Through fieldwork efforts, some deaths will be known but others will go unobserved due to sample members no longer being issued to field or having inconclusive fieldwork outcomes. Using the Household, Income and Labour Dynamics in Australia (HILDA) Survey, three methods are used to examine the implications for non-response correction: i) matching to the national death registry; ii) employing life expectancy tables; and iii) modelling deaths as part of the attrition process.