The Elicitation of Prior Distributions for Bayesian Responsive Survey Design: Historical Data Analysis vs. Literature Review

Responsive Survey Design (RSD) aims to increase the efficiency of survey data collection via live monitoring of paradata and the introduction of protocol changes when survey errors and increased costs seem imminent. Unfortunately, RSD lacks a unifying analytical framework for standardizing its implementation across surveys. Bayesian approaches would seem to be a natural fit for RSD, which relies on real-time updates of prior beliefs about key design parameters. Using real survey data, we evaluate the merits of two approaches to eliciting prior beliefs about the coefficients in daily response propensity models: analyzing historical data from similar surveys and literature review.

[1]  Nicole Kirgis,et al.  Design and Management Strategies for Paradata-Driven Responsive Design: Illustrations from the 2006-2010 National Survey of Family Growth , 2013 .

[2]  Sharon L. Lohr,et al.  Adaptive and responsive survey designs: a review and assessment , 2017 .

[3]  J. Barber,et al.  Design and implementation of an online weekly journal to study unintended pregnancies. , 2011, Vienna yearbook of population research.

[4]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[5]  Moreno Ursino,et al.  Integration of elicited expert information via a power prior in Bayesian variable selection: Application to colon cancer data , 2019, Statistical methods in medical research.

[6]  Frauke Kreuter,et al.  Improving Surveys with Paradata: Analytic Uses of Process Information , 2013 .

[7]  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.

[8]  Haoyu Gu,et al.  THE UTILITY OF ALTERNATIVE COMMERCIAL DATA SOURCES FOR SURVEY OPERATIONS AND ESTIMATION: EVIDENCE FROM THE NATIONAL SURVEY OF FAMILY GROWTH , 2015 .

[9]  Robert M. Groves,et al.  The PAIP Score: A Propensity-Adjusted Interviewer Performance Indicator , 2011 .

[10]  Barry Schouten,et al.  Optimizing quality of response through adaptive survey designs , 2013 .

[11]  Sandjai Bhulai,et al.  Optimal resource allocation in survey designs , 2013, Eur. J. Oper. Res..

[12]  Brady T West,et al.  Responsive Design, Weighting, andVariance Estimation in the 2006-2010 National Survey of Family Growth. , 2013, Vital and health statistics. Series 2, Data evaluation and methods research.

[13]  Michael Peress.  Correcting for Survey Nonresponse Using Variable Response Propensity , 2010 .

[14]  M. A. Best.  Bayesian Approaches to Clinical Trials and Health‐Care Evaluation , 2005 .

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

[16]  Sylvie Chevret,et al.  A practical approach for eliciting expert prior beliefs about cancer survival in phase III randomized trial. , 2009, Journal of clinical epidemiology.

[17]  Chris Mohl.  Research and Responsive Design Options for Survey Data Collection at Statistics Canada , 2007 .

[18]  Annelies G. Blom,et al.  Improving Surveys with Paradata. Analytic Uses of Process Information. Frauke Kreuter (ed.) (2013) , 2015 .

[19]  Carl-Erik Särndal,et al.  Aspects of Responsive Design with Applications to the Swedish Living Conditions Survey , 2013 .

[20]  Femke de Keulenaer,et al.  Using process data to predict attrition from a panel survey: a case study , 2005 .

[21]  Robert M. Groves,et al.  Responsive Survey Design, Demographic Data Collection, and Models of Demographic Behavior , 2011, Demography.

[22]  Andy Peytchev,et al.  Prioritizing Low Propensity Sample Members in a Survey: Implications for Nonresponse Bias , 2014 .