This study investigated the ability of test takers' behaviors during online assessments to detect probable cheating incidents. Specifically, this study focused on the role of time delay and head pose for detection of cheating incidences in a lab-based online testing session. The analysis of a test taker's behavior indicated that not only time delay but also the variation of a student's head pose relative to computer screen had significant statistical relation to cheating behaviors. Additionally, time delay and head-pose variation relative to a computer screen were predictors in a logit model of cheating prediction with an average accuracy of 75.6%. The current algorithm could automatically flag suspicious student behavior for proctors in large-scale online courses during remotely administered exams.