Reduction of nonresponse bias has been a key focus in responsive and adaptive survey designs. Responsive design introduces two or more phases of data collection, each defined by a different protocol. The adaptive design aspect introduces targeting of the interventions to a subset of sample elements. Key in this approach is identification of nonrespondents who, if interviewed, can reduce nonresponse bias in survey estimates. From a design perspective, we need to identify an appropriate model to select targeted cases. From an evaluation perspective, gold standard measures are needed that can provide estimates of nonresponse bias. We designed a bias likelihood approach to selection of sample members to reduce nonresponse bias. Unlike a response propensity approach in which the objective is to maximize the prediction of nonresponse, this new approach deliberately excludes strong predictors of nonresponse that are uncorrelated with survey measures and uses covariates that are of substantive interest to the study. This study also provides a rare opportunity to estimate nonresponse bias, using rich sampling frame information and data from extensive nonresponse follow-up.