The usual methods for analyzing case–cohort studies rely on sometimes not fully efficient weighted estimators. Multiple imputation might be a good alternative because it uses all the data available and approximates the maximum partial likelihood estimator. This method is based on the generation of several plausible complete data sets, taking into account uncertainty about missing values. When the imputation model is correctly defined, the multiple imputation estimator is asymptotically unbiased and its variance is correctly estimated. We show that a correct imputation model must be estimated from the fully observed data (cases and controls), using the case status among the explanatory variable. To validate the approach, we analyzed case–cohort studies first with completely simulated data and then with case–cohort data sampled from two real cohorts. The analyses of simulated data showed that, when the imputation model was correct, the multiple imputation estimator was unbiased and efficient. The observed gain in precision ranged from 8 to 37 per cent for phase‐1 variables and from 5 to 19 per cent for the phase‐2 variable. When the imputation model was misspecified, the multiple imputation estimator was still more efficient than the weighted estimators but it was also slightly biased. The analyses of case–cohort data sampled from complete cohorts showed that even when no strong predictor of the phase‐2 variable was available, the multiple imputation was unbiased, as precised as the weighted estimator for the phase‐2 variable and slightly more precise than the weighted estimators for the phase‐1 variables. However, the multiple imputation estimator was found to be biased when, because of interaction terms, some coefficients of the imputation model had to be estimated from small samples. Multiple imputation is an efficient technique for analyzing case–cohort data. Practically, we suggest building the analysis model using only the case–cohort data and weighted estimators. Multiple imputation can eventually be used to reanalyze the data using the selected model in order to improve the precision of the results. Copyright © 2011 John Wiley & Sons, Ltd.

No abstract

ObjectivesA Demographic and Health Platform was established in Magude in 2015, prior to the deployment of a project aiming to evaluate the feasibility of malaria elimination in southern Mozambique, named the Magude project. This platform aimed to inform the design, implementation and evaluation of the Magude project, through the identification of households and population; and the collection of demographic, health and malaria information.SettingMagude is a rural district of southern Mozambique which borders South Africa. It has nine peripheral health facilities and one referral health centre with an inpatient ward.InterventionA baseline census enumerated and geolocated all the households, and their resident and non-resident members, collecting demographic and socio-economic information, and data on the coverage and usage of malaria control tools. Inpatient and outpatient data during the 5 years (2010 to 2014) before the survey were obtained from the district health authorities. The demographic platform was updated in 2016.ResultsThe baseline census conducted in 2015 reported 48 448 (92.1%) residents and 4133 (7.9%) non-residents, and 10 965 households. Magude’s population is predominantly young, half of the population has no formal education and the main economic activities are agriculture and fishing. Houses are mainly built with traditional non-durable materials and have poor sanitation facilities. Between 2010 and 2014, malaria was the most common cause of all-age inpatient discharges (representing 20% to 40% of all discharges), followed by HIV (12% to 22%) and anaemia (12% to 15%). In early 2015, all-age bed-net usage was between 21.8% and 27.1% and the reported coverage of indoor residual spraying varied across the district between 30.7% and 79%.ConclusionThis study revealed that Magude has limited socio-economic conditions, poor access to healthcare services and low coverage of malaria vector control interventions. Thus, Magude represented an area where it is most pressing to demonstrate the feasibility of malaria elimination.Trial registration numberNCT02914145; Pre-results.