Bias needs to be minimized when conducting survey-based research in order to produce more valid results. Reporting biases are more likely to occur when sensitive behaviors are being investigated. Research suggests that computer-assisted, self-administered interviews (CASIs) may produce more valid reports of sensitive behaviors than will the more traditional survey techniques such as face-to-face interviews (FTFIs). Findings are reported from a study conducted to compare responses to sensitive questions administered through video-enhanced CASIs (V-CASIs) and FTFIs. 280 women of mean age 23 years attending a New Orleans, Louisiana, public family planning or STD clinic from July 1995 to July 1996, diagnosed with Chlamydia trachomatis infection responded to 8 close-ended sexual behavioral questions using both survey techniques in a randomized crossover design. 95% of the women were Black and 71% felt at ease using computers. Although kappa scores indicated good-to-excellent agreement between interview techniques, the women tended to admit to socially undesirable behaviors more often upon V-CASIs than upon FTFIs. 30% of the women gave a discrepant response between V-CASI and FTFI toward social desirability. Women who reported a socially undesirable behavior in V-CASIs were more likely to have a discrepant response. Use of the same logistic regression model to predict condom use yielded different results when data from V-CASIs were used compared with data from FTFIs. Findings suggest that the V-CASI technique can reduce social desirability bias and improve validity in research requiring data on sensitive sexual behaviors.