Does More Balanced Survey Response Imply Less Non-Response Bias?

Schouten, Barry; Cobben, Fannie; Lundquist, Peter; Wagner, James

doi:10.1111/rssa.12152

Cited by 40 publications

(51 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If so, low propensity variation (representativeness) implies low bias risk (see Schouten et al . () for support in the survey non‐response context). In addition, decompositions that quantify propensity variation associated with covariates exist.…”

Section: Introductionmentioning

confidence: 99%

Correlates of Record Linkage and Estimating Risks of Non-Linkage Biases in Business Data Sets

Moore

Smith

Durrant

2017

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

Summary.Researchers often utilize data sets that link information from multiple sources, but non-linkage biases caused by linked and non-linked subject differences are little understood, especially in business data sets. We address these knowledge gaps by studying biases in linkable 2010 UK Small Business Survey data sets.We identify correlates of business linkage propensity, and also for the first time its components: consent to linkage and register identifier appendability. As well, we take a novel approach to evaluating non-linkage bias risks, by computing data set representativeness indicators (comparable, decomposable sample subset similarity measures). We find that the main impacts on linkage propensities and bias risks are due to consenternon-consenter differences explicable given business survey response processes, and differences between subjects with and without identifiers caused by register undercoverage of very small businesses. We then discuss consequences for the analysis of linked business data sets, and implications of the evaluation methods we introduce for linked data set producers and users.

show abstract

Section: Introductionmentioning

confidence: 99%

Correlates of Record Linkage and Estimating Risks of Non-Linkage Biases in Business Data Sets

Moore

Smith

Durrant

2017

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

show abstract

“…The data collection is undeniably an integral part of the inference process, particularly important in times of high survey nonresponse. Several recent articles seek evidence, theoretical and empirical, on possible favorable effects of a response that is made to be more representative or better balanced, for example, Schouten et al (2016), Schouten et al (2013), Lundquist and Särndal (2013), Särndal et al (2016). These articles point to some, although not strongly pronounced, favorable effect of balancing.…”

Section: Responsive Designmentioning

confidence: 99%

Inconsistent Regression and Nonresponse Bias: Exploring Their Relationship as a Function of Response Imbalance

Lundquist

2017

Journal of Official Statistics

Self Cite

View full text Add to dashboard Cite

One objective of adaptive data collection is to secure a better balanced survey response. Methods exist for this purpose, including balancing with respect to selected auxiliary variables. Such variables are also used at the estimation stage for (calibrated) nonresponse weighting adjustment.Earlier research has shown that the use of auxiliary information at the estimation stage can reduce bias, perhaps considerably, but without eliminating it. The question is: would it have contributed further to bias reduction if, prior to estimation, that information had also been used in data collection, to secure a more balanced set of respondents? If the answer is yes, there is clear incentive, from the point of view of better accuracy in the estimates, to practice adaptive survey design, otherwise perhaps not.A key question is how the regression relationship between the survey variable and the auxiliary vector presents itself in the sample as opposed to the response. Strength in the relationship is helpful but is not the only consideration. The dilemma with nonresponse is one of inconsistent regression: a regression model appropriate for the sample often fails for the responding subset, because nonresponse is selective, non-random.In this article, we examine how nonresponse bias in survey estimates depends on regression inconsistency, both seen as functions of response imbalance. As a measure of bias we use the deviation of the calibration adjusted estimator from the unbiased estimate under full response. We study how the deviation and the regression inconsistency depend on the imbalance. We observe in empirical work that both can be reduced, to a degree, by efforts to reduce imbalance by an adaptive data collection.

show abstract

“…Partial indicators provide information on the contribution of single specified variables (and their categories) to a lack of representative response [37]. Rindicators can also be used to derive bias intervals for commonly used estimators [9].…”

Section: Sample Compositionmentioning

confidence: 99%

“…However, it is not standard practice yet. [9] provides theoretical and empirical evidence that a more balanced response achieved by the implementation of adaptive survey designs coincides with less non-response bias, even after adjustment.…”

Section: Introductionmentioning

confidence: 99%

Targeted letters: Effects on sample composition and item non-response

Bianchi¹,

Biffignandi²

2017

SJI

View full text Add to dashboard Cite

Abstract. General population surveys as well as business surveys are affected by low response rates. There is a need to investigate possible ways to increase participation in surveys and to motivate interviewee in answering questionnaires. Even in official statistics the problem is relevant since lack of motivation undermines not only participation to the survey, but it is related to the timeliness in participation, the quality of the answers and hence the quality of the measurements of socio-economic phenomena. A possible approach to cope with this problem, which has received attention in recent years, is targeted design. In targeted designs, several survey features may be the object of interventions (timing of contact, number of contact attempts, mode of contact, interviewers' assignment, communication features, etc.). In our paper, we consider the invitation letter, which is one possible targeted feature. This is related to motivation to respond to surveys and to respond accurately, completely, and timely. We analyze a case study in the UK Household Longitudinal Study Innovation Panel. At wave 6 of the panel, a randomized experiment was carried out to study the effects of targeted initial letters [1]. We investigate effects of targeted initial letters on sample composition, representativity, and item non-response.

show abstract

Does More Balanced Survey Response Imply Less Non-Response Bias?

Cited by 40 publications

References 22 publications

Correlates of Record Linkage and Estimating Risks of Non-Linkage Biases in Business Data Sets

Correlates of Record Linkage and Estimating Risks of Non-Linkage Biases in Business Data Sets

Inconsistent Regression and Nonresponse Bias: Exploring Their Relationship as a Function of Response Imbalance

Targeted letters: Effects on sample composition and item non-response

Contact Info

Product

Resources

About