Abstract. TangentBoost is a robust boosting algorithm. The method combines loss function and weak classi…ers. In addition, TangentBoost gives penalties not only misclassi…cation but also true classi…cation margin in order to get more stable classi…ers. Despite the fact that the method is good one in object tracking, propensity scores are obtained improperly in the algorithm. The problem causes mislabeling of observations in the statistical classi…cation. In this paper, there is a correction proposal for TangentBoost algorithm. After the correction on the algorithm, there is a simulation study for the new algorithm. The results show that correction on the algorithm is useful for binary classi…cation.