Abstract
BackgroundFocus groups, rapid assessment procedures, key informant interviews and institutional reviews of local health services provide valuable insights on health service resources and performance. A long-standing challenge of health planning is to combine this sort of qualitative evidence in a unified analysis with quantitative evidence from household surveys. A particular challenge in this regard is to take account of the neighbourhood or clustering effects, recognising that these can be informative or incidental.MethodsAn example of food aid and food sufficiency from the Bosnian emergency (1995-96) illustrates two Lamothe cluster-adjustments of the Mantel Haenszel (MH) procedure, one assuming a fixed odds ratio and the other allowing for informative clustering by not assuming a fixed odds ratio. We compared these with conventional generalised estimating equations and a generalised linear mixed (GLMM) model, using a Laplace adjustment.ResultsThe MH adjustment assuming incidental clustering generated a final model very similar to GEE. The adjustment that does not assume a fixed odds ratio produced a final multivariate model and effect sizes very similar to GLMM.DiscussionIn medium or large data sets with stratified last stage random sampling, the cluster adjusted MH is substantially more conservative than the naïve MH computation. In the example of food aid in the Bosnian crisis, the cluster adjusted MH that does not assume a fixed odds ratio produced similar results to the GLMM, which identified informative clustering.
Highlights
In public health we often need to understand the change in outcomes associated with a given programme intervention
A household cross-sectional survey might identify the proportion of households covered by an intervention, like food aid
The challenge is to work out what the difference in status has to do with the programme input, in the light of other differences between households that receive food aid and those that do not
Summary
In public health we often need to understand the change in outcomes associated with a given programme intervention. Repeat surveys might detect a change in status, like household food security. The challenge is to work out what the difference in status (improved household food security) has to do with the programme input (management of food aid), in the light of other differences between households that receive food aid and those that do not. Large scale pragmatic randomised controlled trials can help to sort out causality by demonstrating benefit in. These do not always produce clear evidence, but their relevance to decisions about causal relations is increased when analysis allows exclusion of other explanations (apart from the programme in question) for differences between two time points or between two subgroups. A long-standing challenge of health planning is to combine this sort of qualitative evidence in a unified analysis with quantitative evidence from household surveys. A particular challenge in this regard is to take account of the neighbourhood or clustering effects, recognising that these can be informative or incidental
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have