Multiple Auxiliary Variables in Nonresponse Adjustment

Prior work has shown that effective survey nonresponse adjustment variables should be highly correlated with both the propensity to respond to a survey and the survey variables of interest. In practice, propensity models are often used for nonresponse adjustment with multiple auxiliary variables as predictors. These auxiliary variables may be positively or negatively associated with survey participation, they may be correlated with each other, and can have positive or negative relationships with the survey variables. Yet the consequences for nonresponse adjustment of these conditions are not known to survey practitioners. Simulations are used here to examine the effects of multiple auxiliary variables with opposite relationships with survey participation and the survey variables. The results show that bias and mean square error of adjusted respondent means are substantially different when the predictors have relationships of the same directions compared to when they have opposite directions with either propensity or the survey variables. Implications for nonresponse adjustment and responsive designs will be discussed.

[1]  Jeremiah P. Banda.  Nonsampling errors in surveys , 2003 .

[2]  R. Groves.  Nonresponse Rates and Nonresponse Bias in Household Surveys , 2006 .

[3]  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.

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

[5]  R. Little.  Survey Nonresponse Adjustments for Estimates of Means , 1986 .

[6]  K. Olson.  An Investigation of the Nonresponse - Measurement Error Nexus. , 2007 .

[7]  Karen E Davis,et al.  National Survey of Family Growth, Cycle 6: sample design, weighting, imputation, and variance estimation. , 2006, Vital and health statistics. Series 2, Data evaluation and methods research.

[8]  R. Little,et al.  Does Weighting for Nonresponse Increase the Variance of Survey Means? (Conference Paper) , 2004 .

[9]  F. Kreuter,et al.  Using Proxy Measures of Survey Outcomes in Post-Survey Adjustments : Examples from the European Social Survey ( ESS ) , 2007 .

[10]  Phawn M. Letourneau,et al.  Nonresponse in the American Time Use Survey , 2008 .

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

[12]  D. Rubin,et al.  The central role of the propensity score in observational studies for causal effects , 1983 .

[13]  Frauke Kreuter,et al.  Analyzing contact sequences in call record data. Potential and limitations of sequence indicators for nonresponse adjustments in the European Social Survey , 2009 .

[14]  Robert M. Groves,et al.  Nonresponse in Household Interview Surveys: Groves/Nonresponse , 1998 .

[15]  Kosuke Imai,et al.  Survey Sampling , 1998, Nov/Dec 2017.

[16]  E. Ziegel,et al.  Nonresponse In Household Interview Surveys , 1998 .

[17]  C Loehlin John,et al.  Latent variable models: an introduction to factor, path, and structural analysis , 1986 .

[18]  Andy Peytchev,et al.  Using Interviewer Observations To Improve Nonresponse Adjustments: NES 2004 , 2007 .

[19]  Ting Yan.  Using Proxy Measures of the Survey Variables in Post-Survey Adjustments in a Transportation Survey , 2007 .

[20]  A. Fielding,et al.  Non‐Sampling Errors in Surveys , 1995 .

[21]  R. Little,et al.  On weighting the rates in non‐response weights , 2003, Statistics in medicine.