|
Abstract:
|
More and more large-scale surveys have implemented responsive design strategies in response to falling sample yields and response rates and the availability of paradata. These methods have helped to build a framework for visualizing and reacting to changing circumstances during the data collection process. In the 2003 National Assessment of Adult Literacy, new strategies were formulated for focusing follow-up attempts based on observed sample monitoring indicators, which were refined during the 2012 Programme for the International Assessment of Adult Competencies (PIAAC) survey. The need to sample specific domains in the 2014 PIAAC National Supplement has led to further efforts to find methods that meet sample yield targets with minimal impact on response rates, nonresponse bias, and cost. We focus on three components: projecting whether a sample yield target will be achieved and determining if extra cases need to be released; prioritizing cases; and providing guidelines for the number of contact attempts. The effectiveness and impact of these components will be tested on the PIAAC sample data. Strategies that need to be customized for the literacy study will also be presented.
|
