There is increased interest in using commercial providers for improving access to quality malaria treatment. Understanding their current role is an essential first step, notably in terms of the volume of diagnostics and anti-malarials they sell. Sales volume data can be used to measure the importance of different provider and product types, frequency of parasitological diagnosis and impact of interventions. Several methods for measuring sales volumes are available, yet all have methodological challenges and evidence is lacking on the comparability of different methods.
Using sales volume data on anti-malarials and rapid diagnostic tests (RDTs) for malaria collected through provider recall (RC) and retail audits (RA), this study measures the degree of agreement between the two methods at wholesale and retail commercial providers in Cambodia following the Bland-Altman approach. Relative strengths and weaknesses of the methods were also investigated through qualitative research with fieldworkers.
A total of 67 wholesalers and 107 retailers were sampled. Wholesale sales volumes were estimated through both methods for 62 anti-malarials and 23 RDTs and retail volumes for 113 anti-malarials and 33 RDTs. At wholesale outlets, RA estimates for anti-malarial sales were on average higher than RC estimates (mean difference of four adult equivalent treatment doses (95% CI 0.6-7.2)), equivalent to 30% of mean sales volumes. For RDTs at wholesalers, the between-method mean difference was not statistically significant (one test, 95% CI −6.0-4.0). At retail outlets, between-method differences for both anti-malarials and RDTs increased with larger volumes being measured, so mean differences were not a meaningful measure of agreement between the methods. Qualitative research revealed that in Cambodia where sales volumes are small, RC had key advantages: providers were perceived to remember more easily their sales volumes and find RC less invasive; fieldworkers found it more convenient; and it was cheaper to implement than RA.
Both RA and RC had implementation challenges and were prone to data collection errors. Choice of empirical methods is likely to have important implications for data quality depending on the study context.