“Disease Prevalence Estimation and Binary Regression Methods for Respondent-Driven Sampling with Uncertain Outcomes” is the name of a study that came third in the Introductory Scientific Research category in the 2022 Beatriz Neves Awards, organized by the Brazilian Society of Applied and Computational Mathematics (SBMAC). The paper was written by Lucas Moschen, a student at Fundação Getulio Vargas’ School of Applied Mathematics (FGV EMAp), supported by Professor Luiz Max de Carvalho.

According to Moschen, disease transmission in communities that are difficult to access is a major public health problem. These communities include heavy drug users, men who have sex with men, refugees, activists and sex workers, who engage in behavior that is criminalized or stigmatized by society. For this reason, researchers are unable to survey samples of these groups in traditional ways, such as household or phone surveys. To mitigate the effects of diseases in these groups, it is extremely important to understand which variables are related to each disease and to quantify the proportion of sick individuals.

Respondent-driven sampling (RDS) is a popular approach to obtain samples from hard-to-access groups. It consists of encouraging participants themselves to recruit their peers, receiving rewards for participating and also for recruiting. The main objective of Moschen’s study was to develop Bayesian models to estimate the prevalence of diseases in hard-to-access groups. In particular, statistical and computational tools were developed to make it possible to estimate the prevalence of a disease when the diagnostic method is imperfect.

SBMAC set up the Beatriz Neves Awards to encourage undergraduate students to take part in introductory scientific research activities in the field of applied and computational mathematics. Any student who has produced a paper in this area may submit it to this awards scheme. The prizes are handed out annually at the National Congress for Applied and Computational Mathematics. The awards are named for Professor Beatriz Neves (1935-1986), who worked at Rio de Janeiro Federal University’s Mathematics Institute.

To access the complete study, click here.