Model Assisted Statistics and Applications 8 (2013) 135–141 135 DOI 10.3233/MAS-130256 IOS Press Statistical models to estimate male-to-female HIV transmission probabilities Hrishikesh Chakraborty Department of Epidemiology and Biostatistics, Arnold School of Public Health, The University of South Carolina, 800 Sumter Street, Suite 208-D, Columbia, SC 29208, USA Tel.: +1 803 777 3170; Fax: +1 803 777 2524; E-mail: rishic@mailbox.sc.edu Abstract. To develop effective public-health intervention strategies for preventing person-to-person disease transmission, it is extremely essential to know the underlying biological processes and the probability of transmission. However, it is unethical to design studies to estimate the probability of person-to-person disease transmission because such studies would involve infecting an uninfected person with a disease. Statistical modeling is a very important technique used to estimate disease transmission probabilities among individuals. By using data from different independent studies, researchers may be able to obtain enough information about an infected person’s infectiousness and the susceptibility of an uninfected person to estimate disease trans- mission probabilities. In this paper, we developed a statistical modeling technique to estimate probabilities of person-to-person disease transmission from an infected to an uninfected person. We used this new modeling technique to estimate the probability of male-to-female, penile – vaginal human immunodeficiency virus (HIV) transmission in one sexual contact. We developed two different sets of male-to-female HIV transmission probability estimates for different infectiousness and susceptibility values using two models. This newly developed modeling technique can be used to estimate person-to-person transmission probabilities for different diseases and routes of transmission. Keywords: Statistical model, transmission probabilities, infectious diseases, HIV 1. Background To effectively control human diseases, it is important to be acquainted with the probability of person-to-person disease transmission in one contact. Although an understanding of the probability of disease transmission is very important to scientists, it is unethical to investigate disease transmission in a study setting because it would involve infection of an uninfected person. As a result, statistical models are most often used to model person-to-person disease transmission probabilities. These models are confounded by the difficulty of collecting appropriate empirical data from infected and uninfected individuals and also by different types of estimation used in statistical modeling. For example, most published estimates of the probability of sexual transmission of human immunodeficiency virus (HIV) have assumed constant infectivity between couples, ignoring the possibility that acquired immunity might reduce the efficiency of transmission [1]. The main obstacle to estimating person-to-person disease transmission probability in one contact is the availability of relevant data. In some situations, it is impossible to obtain the data to explore the biological relationship; however, partial data from different independent sources are often available because different scientists become interested in different components of the biological process of transmission. For instance, to estimate the male-to-female HIV transmission probability, we need to know the male transmitter cell distribution and the female receptor cell distribution, and to have data on the efficiency of transmission. Currently, researchers tend to study aspects of HIV transmission separately. Some studies observe HIV-infected males to obtain data on HIV concentration in seminal plasma; healthy females to identify and quantify female recep- tor cells; or use epidemiological techniques to estimate the HIV transmission probabilities. It becomes a statistical challenge to model the independent information generated from the individual studies to draw a single conclusion. ISSN 1574-1699/13/$27.50 c  2013 – IOS Press and the authors. All rights reserved