Abstract

Sensitive questions like HIV status may cause biased estimation of unknown population parameters as well as increase in the variance of the estimates due to evasive responses. The randomized response techniques (RRT) can be used to avoid the concealment of information or evasive answers. The RRT guarantees the anonymity of respondents in surveys aimed at determining the frequency of stigmatic, embarrassing or criminal behaviour where direct techniques for data collection may induce respondents to refuse to answer or give false responses. Different randomized response models (RRMs) have been devised in the past decades for dealing with sensitive items; which usually involve the use of random devices, such as dice or cards to collect reliable data on sensitive issues. Most of these RRMs have been proposed without some specific applications to HIV seroprevalence surveys. The motivation was to improve upon the existing RRMs as well as to apply them to estimate HIV seroprevalence rates. The objectives were to use research frontier to devise a mixed-stratified RRMs, use same to estimate HIV seroprevalence rates in a given population and compare results with the existing seroprevalence rates. Furthermore, the procedure of the field work and sampling design were well coordinated for the target population of 3,740 people aged 18 years and above using a sample size of 550. Furthermore, the model was used to estimate the HIV seroprevalence rate in a small population of adults attending a clinic in Kaduna, Nigeria. The model estimated the HIV seroprevalence rate as 8.74% with a standard error of 0.0134 and a 95% confidence interval of 6.1 and 11.4%, respectively. Accordingly, the sentinel projected seroprevalence rate, using the Epidemic Projection Package (EPP), for the next ten years (2013) was 9.7%; very consistent with the 95% confidence interval. Hence, the RRTs herein can serve as new viable methods for HIV seroprevalence surveys.

Key words: Randomized response techniques, randomized response models, seroprevalence rates, mixed-stratified, design parameter, efficiency, sentinel surveys, stratified random sampling.