Use of Paradata in a Responsive Design Framework to Manage a Field Data Collection

Every household survey confronts uncertainty in the performance of its recruitment protocol. Diverse modern populations present the data collecting organization with a myriad of practical problems of contacting household units, identifying the proper respondents, gaining their cooperation, and finding appropriate times to interview them. Responsive survey designs (Groves and Heeringa, 2006) use paradata to monitor costs and response rate features of a survey during data collection and actively intervene into the recruitment protocol to effect changes in the production process of interviews. When the paradata are informative about costs and potential error properties of the key estimates to be computed from the survey, responsive designs have the potential to improve the quality-per-unit-cost properties of a survey. This paper uses a simple production model articulating inputs to the data collection, the quality of the sample cases available, and the costs and data records produced. This model motivates a set of paradata that might be useful in managing a survey. The paper presents three examples of management interventions based on paradata collected throughout the Continuous National Survey of Family Growth (NSFG), and evaluates the effectiveness of these interventions. Use of Paradata in a Responsive Design Framework to Manage a Field Data Collection 3

[1]  Robert M. Groves,et al.  Using variation in response rates of demographic subgroups as evidence of nonresponse bias in survey estimates , 2009 .

[2]  Mick P. Couper,et al.  MEASURING SURVEY QUALITY IN A CASIC ENVIRONMENT , 2002 .

[3]  Clare K. Purvis,et al.  Using the American Community Survey: Benefits and Challenges , 2006 .

[4]  Jelke Bethlehem,et al.  Indicators for the representativeness of survey response , 2009 .

[5]  Stephen E. Fienberg,et al.  From the inside out and the outside in: Combining experimental and sampling structures , 1988 .

[6]  Gabriele B. Durrant,et al.  Using paradata to predict best times of contact, conditioning on household and interviewer influences , 2011 .

[7]  S E Fienberg,et al.  Combining Cognitive and Statistical Approaches to Survey Design , 1989, Science.

[8]  R. Groves,et al.  Planning and development of the continuous National Survey of Family Growth. , 2009, Vital and health statistics. Ser. 1, Programs and collection procedures.

[9]  Achim Koch,et al.  Improving Survey Response: Lessons Learned from the European Social Survey , 2010 .

[10]  Peter Granda,et al.  Plan and operation of Cycle 6 of the National Survey of Family Growth. , 2005, Vital and health statistics. Ser. 1, Programs and collection procedures.

[11]  D. Rubin,et al.  Statistical Analysis with Missing Data , 1988 .

[12]  Sarah F. Riley,et al.  Reduction of Nonresponse Bias in Surveys through Case Prioritization , 2010 .

[13]  Robert M. Groves,et al.  Using proxy measures and other correlates of survey outcomes to adjust for non‐response: examples from multiple surveys , 2010 .

[14]  B. West.  An Examination of the Quality and Utility of Interviewer Estimates of Household Characteristics in the National Survey of Family Growth , 2010 .

[15]  R. Groves,et al.  The 2006-2010 National Survey of Family Growth: sample design and analysis of a continuous survey. , 2010, Vital and health statistics. Series 2, Data evaluation and methods research.

[16]  Mick Couper,et al.  The Use of Paradata in Survey Research , 2022 .

[17]  Robert M. Groves,et al.  Responsive design for household surveys: tools for actively controlling survey errors and costs , 2006 .

[18]  A. Chandra,et al.  Fertility of men and women aged 15-44 years in the United States: National Survey of Family Growth, 2006-2010. , 2012, National health statistics reports.

[19]  R. Groves,et al.  Survey Errors and Survey Costs. , 1991 .