For improving the quality of survey dat a of sensitive character, we suggest a conditional in direct survey method. In th at method, only the respondents who answer directly to the less sensitive question respond indirectly to the more sensitive one by using the one sample unrelated question randomized response technique with the known $pi_y$, the true proportion of unrelated group Y. We extend it to two sample method when $pi_y$ is unknown. We also consider the case that people who possess less sensitive character answer untruthfully. Finally we compare our method with the methods of Greenberg et al. and Carr et al..