Objectives: To identify psychosocial predictors of Trichomonas vaginalis infection among low income African-American adolescent females living in a high risk urban area of the United States. Methods: Baseline plus 6 and 12 month follow up data collected as part of an HIV prevention intervention trial were utilised. The baseline sample consisted of 522 African-American females, 14-18 years of age. Recruitment sites were located in low income neighbourhoods of Birmingham, Alabama, characterised by high rates of unemployment, substance abuse, violence, teenage pregnancy, and sexually transmitted infections. Self administered vaginal swab specimens were cultured for T vaginalis. Baseline measures collected as part of a self administered survey and face to face interviews were used to predict subsequent infection with T vaginalis at any of the three assessment periods conducted over the span of 1 year. Results: At baseline, 12.9% were diagnosed with T vaginalis. At the 6 and 12 month follow ups, T vaginalis was diagnosed in 8.9% and 10.2%, respectively. The strongest multivariate predictor of T vaginalis infection was biologically confirmed marijuana use; those using marijuana were more than six times as likely to test positive for T vaginalis (adjusted odds ratio (AOR) = 6.2, p = 0.0003). Other multivariate predictors were reporting that typical sex partners were at least 5 years older (AOR = 2.6; p = 0.005), reporting sex with non-steady partners (AOR = 1.9; p = 0.02), and history of delinquency (AOR = 1.3; p = 0.02). The odds of testing positive increased by 31% for every one unit increase on a six item scale measure of delinquency. Conclusions: Infection with T vaginalis was common and significant multivariate predictors comprised a constellation of problem behaviours, each of which are potentially amenable to behavioural intervention.