Cluster designs to assess the prevalence of acute malnutrition by lot quality assurance sampling: a validation study by computer simulation

Optimal design of multiple-objective Lot Quality Assurance Sampling (LQAS) plans

Lot Quality Assurance Sampling (LQAS) plans are widely used for health monitoring purposes. We propose a systematic approach to design multiple-objective LQAS plans that meet user-specified type 1 and 2 error rates and targets for selected diagnostic accuracy metrics. These metrics may include sensitivity, specificity, positive predictive value, and negative predictive value in high or low anticipated prevalence rate populations. We use Mixed Integer Nonlinear Programming (MINLP) tools to implement our design methodology. Our approach is flexible in that it can directly generate classic LQAS plans that control error rates only and find optimal LQAS plans that meet multiple objectives in terms of diagnostic metrics. We give examples, compare results with the classic LQAS and provide an application using a malaria outcome indicator survey in Mozambique.

Using lot quality assurance sampling to assess access to water, sanitation and hygiene services in a refugee camp setting in South Sudan: a feasibility study

Background

Humanitarian agencies working in refugee camp settings require rapid assessment methods to measure the needs of the populations they serve. Due to the high level of dependency of refugees, agencies need to carry out these assessments. Lot Quality Assurance Sampling (LQAS) is a method commonly used in development settings to assess populations living in a project catchment area to identify their greatest needs. LQAS could be well suited to serve the needs of refugee populations, but it has rarely been used in humanitarian settings. We adapted and implemented an LQAS survey design in Batil refugee camp, South Sudan in May 2013 to measure the added value of using it for sub-camp level assessment.

Methods

Using pre-existing divisions within the camp, we divided the Batil catchment area into six contiguous segments, called ‘supervision areas’ (SA). Six teams of two data collectors randomly selected 19 respondents in each SA, who they interviewed to collect information on water, sanitation, hygiene, and diarrhoea prevalence. These findings were aggregated into a stratified random sample of 114 respondents, and the results were analysed to produce a coverage estimate with 95% confidence interval for the camp and to prioritize SAs within the camp.

Results

The survey provided coverage estimates on WASH indicators as well as evidence that areas of the camp closer to the main road, to clinics and to the market were better served than areas at the periphery of the camp. This assumption did not hold for all services, however, as sanitation services were uniformly high regardless of location. While it was necessary to adapt the standard LQAS protocol used in low-resource communities, the LQAS model proved to be feasible in a refugee camp setting, and program managers found the results useful at both the catchment area and SA level.

Conclusions

This study, one of the few adaptations of LQAS for a camp setting, shows that it is a feasible method for regular monitoring, with the added value of enabling camp managers to identify and advocate for the least served areas within the camp. Feedback on the results from stakeholders was overwhelmingly positive.

Choosing a Cluster Sampling Design for Lot Quality Assurance Sampling Surveys

Lot quality assurance sampling (LQAS) surveys are commonly used for monitoring and evaluation in resource-limited settings. Recently several methods have been proposed to combine LQAS with cluster sampling for more timely and cost-effective data collection. For some of these methods, the standard binomial model can be used for constructing decision rules as the clustering can be ignored. For other designs, considered here, clustering is accommodated in the design phase. In this paper, we compare these latter cluster LQAS methodologies and provide recommendations for choosing a cluster LQAS design. We compare technical differences in the three methods and determine situations in which the choice of method results in a substantively different design. We consider two different aspects of the methods: the distributional assumptions and the clustering parameterization. Further, we provide software tools for implementing each method and clarify misconceptions about these designs in the literature. We illustrate the differences in these methods using vaccination and nutrition cluster LQAS surveys as example designs. The cluster methods are not sensitive to the distributional assumptions but can result in substantially different designs (sample sizes) depending on the clustering parameterization. However, none of the clustering parameterizations used in the existing methods appears to be consistent with the observed data, and, consequently, choice between the cluster LQAS methods is not straightforward. Further research should attempt to characterize clustering patterns in specific applications and provide suggestions for best-practice cluster LQAS designs on a setting-specific basis.

Extending cluster lot quality assurance sampling designs for surveillance programs

Lot quality assurance sampling (LQAS) has a long history of applications in industrial quality control. LQAS is frequently used for rapid surveillance in global health settings, with areas classified as poor or acceptable performance on the basis of the binary classification of an indicator. Historically, LQAS surveys have relied on simple random samples from the population; however, implementing two-stage cluster designs for surveillance sampling is often more cost-effective than simple random sampling. By applying survey sampling results to the binary classification procedure, we develop a simple and flexible nonparametric procedure to incorporate clustering effects into the LQAS sample design to appropriately inflate the sample size, accommodating finite numbers of clusters in the population when relevant. We use this framework to then discuss principled selection of survey design parameters in longitudinal surveillance programs. We apply this framework to design surveys to detect rises in malnutrition prevalence in nutrition surveillance programs in Kenya and South Sudan, accounting for clustering within villages. By combining historical information with data from previous surveys, we design surveys to detect spikes in the childhood malnutrition rate.

Estimation after classification using lot quality assurance sampling: corrections for curtailed sampling with application to evaluating polio vaccination campaigns

OBJECTIVES

To assess the bias incurred when curtailment of Lot Quality Assurance Sampling (LQAS) is ignored, to present unbiased estimators, to consider the impact of cluster sampling by simulation and to apply our method to published polio immunization data from Nigeria.

METHODS

We present estimators of coverage when using two kinds of curtailed LQAS strategies: semicurtailed and curtailed. We study the proposed estimators with independent and clustered data using three field-tested LQAS designs for assessing polio vaccination coverage, with samples of size 60 and decision rules of 9, 21 and 33, and compare them to biased maximum likelihood estimators. Lastly, we present estimates of polio vaccination coverage from previously published data in 20 local government authorities (LGAs) from five Nigerian states.

RESULTS

Simulations illustrate substantial bias if one ignores the curtailed sampling design. Proposed estimators show no bias. Clustering does not affect the bias of these estimators. Across simulations, standard errors show signs of inflation as clustering increases. Neither sampling strategy nor LQAS design influences estimates of polio vaccination coverage in 20 Nigerian LGAs. When coverage is low, semicurtailed LQAS strategies considerably reduces the sample size required to make a decision. Curtailed LQAS designs further reduce the sample size when coverage is high.

CONCLUSIONS

Results presented dispel the misconception that curtailed LQAS data are unsuitable for estimation. These findings augment the utility of LQAS as a tool for monitoring vaccination efforts by demonstrating that unbiased estimation using curtailed designs is not only possible but these designs also reduce the sample size.

The effect of clustering on lot quality assurance sampling: a probabilistic model to calculate sample sizes for quality assessments

BACKGROUND

Traditional Lot Quality Assurance Sampling (LQAS) designs assume observations are collected using simple random sampling. Alternatively, randomly sampling clusters of observations and then individuals within clusters reduces costs but decreases the precision of the classifications. In this paper, we develop a general framework for designing the cluster(C)-LQAS system and illustrate the method with the design of data quality assessments for the community health worker program in Rwanda.

RESULTS

To determine sample size and decision rules for C-LQAS, we use the beta-binomial distribution to account for inflated risk of errors introduced by sampling clusters at the first stage. We present general theory and code for sample size calculations.The C-LQAS sample sizes provided in this paper constrain misclassification risks below user-specified limits. Multiple C-LQAS systems meet the specified risk requirements, but numerous considerations, including per-cluster versus per-individual sampling costs, help identify optimal systems for distinct applications.

CONCLUSIONS

We show the utility of C-LQAS for data quality assessments, but the method generalizes to numerous applications. This paper provides the necessary technical detail and supplemental code to support the design of C-LQAS for specific programs.

Intervene before leaving: clustered lot quality assurance sampling to monitor vaccination coverage at health district level before the end of a yellow fever and measles vaccination campaign in Sierra Leone in 2009

Background

In November 2009, Sierra Leone conducted a preventive yellow fever (YF) vaccination campaign targeting individuals aged nine months and older in six health districts. The campaign was integrated with a measles follow-up campaign throughout the country targeting children aged 9–59 months. For both campaigns, the operational objective was to reach 95% of the target population. During the campaign, we used clustered lot quality assurance sampling (C-LQAS) to identify areas of low coverage to recommend timely mop-up actions.

Methods

We divided the country in 20 non-overlapping lots. Twelve lots were targeted by both vaccinations, while eight only by measles. In each lot, five clusters of ten eligible individuals were selected for each vaccine. The upper threshold (UT) was set at 90% and the lower threshold (LT) at 75%. A lot was rejected for low vaccination coverage if more than 7 unvaccinated individuals (not presenting vaccination card) were found. After the campaign, we plotted the C-LQAS results against the post-campaign coverage estimations to assess if early interventions were successful enough to increase coverage in the lots that were at the level of rejection before the end of the campaign.

Results

During the last two days of campaign, based on card-confirmed vaccination status, five lots out of 20 (25.0%) failed for having low measles vaccination coverage and three lots out of 12 (25.0%) for low YF coverage. In one district, estimated post-campaign vaccination coverage for both vaccines was still not significantly above the minimum acceptable level (LT = 75%) even after vaccination mop-up activities.

Conclusion

C-LQAS during the vaccination campaign was informative to identify areas requiring mop-up activities to reach the coverage target prior to leaving the region. The only district where mop-up activities seemed to be unsuccessful might have had logistical difficulties that should be further investigated and resolved.

Clustered lot quality assurance sampling: a tool to monitor immunization coverage rapidly during a national yellow fever and polio vaccination campaign in Cameroon, May 2009

We used the clustered lot quality assurance sampling (clustered-LQAS) technique to identify districts with low immunization coverage and guide mop-up actions during the last 4 days of a combined oral polio vaccine (OPV) and yellow fever (YF) vaccination campaign conducted in Cameroon in May 2009. We monitored 17 pre-selected districts at risk for low coverage. We designed LQAS plans to reject districts with YF vaccination coverage <90% and with OPV coverage <95%. In each lot the sample size was 50 (five clusters of 10) with decision values of 3 for assessing OPV and 7 for YF coverage. We 'rejected' 10 districts for low YF coverage and 14 for low OPV coverage. Hence we recommended a 2-day extension of the campaign. Clustered-LQAS proved to be useful in guiding the campaign vaccination strategy before the completion of the operations.