Explore the vast range of titles available.

The growth of non-response rates for social science surveys has led to increased concern about the risk of non-response bias. Unfortunately, the non-response rate is a poor indicator of when non-response bias is likely to occur. We consider in this paper a set of alternative indicators. A large-scale simulation study is used to explore how each of these indicators performs in a variety of circumstances. Although, as expected, none of the indicators fully depict the impact of non-response in survey estimates, we discuss how they can be used when creating a plausible account of the risks for non-response bias for a survey. We also describe an interesting characteristic of the fraction of missing information that may be helpful in diagnosing not-missing-at-random mechanisms in certain situations.

Survey research methodology is widely used in marketing, and it is important for both the field and individual researchers to follow stringent guidelines to ensure that meaningful insights are attained. To assess the extent to which marketing researchers are utilizing best practices in designing, administering, and analyzing surveys, we review the prevalence of published empirical survey work during the 2006–2015 period in three top marketing journals—Journal of the Academy of Marketing Science (JAMS), Journal of Marketing (JM), and Journal of Marketing Research (JMR)—and then conduct an in-depth analysis of 202 survey-based studies published in JAMS. We focus on key issues in two broad areas of survey research (issues related to the choice of the object of measurement and selection of raters, and issues related to the measurement of the constructs of interest), and we describe conceptual considerations related to each specific issue, review how marketing researchers have attended to these issues in their published work, and identify appropriate best practices.

Hot deck imputation is a method for handling missing data in which each missing value is replaced with an observed response from a “similar” unit. Despite being used extensively in practice, the theory is not as well developed as that of other imputation methods. We have found that no consensus exists as to the best way to apply the hot deck and obtain inferences from the completed data set. Here we review different forms of the hot deck and existing research on its statistical properties. We describe applications of the hot deck currently in use, including the U.S. Census Bureau's hot deck for the Current Population Survey (CPS). We also provide an extended example of variations of the hot deck applied to the third National Health and Nutrition Examination Survey (NHANES III). Some potential areas for future research are highlighted. L'imputation hot deck est une méthode de gestion des données manquantes dans laquelle chaque valeur manquante est remplacée par une réponse observée à partir d'une unité “similaire.” Bien qu'elle soit largement utilisée en pratique, sa théorie n'est pas aussi développée que celle des autres méthodes d'imputation. Nous avons constaté qu'il n'existe aucun consensus quant à la meilleure faon d'appliquer les hot deck et obtenir des inférences à partir de la série de données complète. Ici, nous passons en revue les différentes formes de hot deck et les recherches existantes sur ses propriétés statistiques. Nous décrivons les applications du hot deck actuellement utilisées, y compris le hot deck du Bureau US du recensement pour la Current Population Survey (CPS). Nous proposons aussi des exemples nombreux de variations du hot deck à la troisième National Health and Nutrition Examination Survey (NHANES III). Certains domaines possibles de recherches futures sont mises en évidence.

Non-response weighting is a commonly used method to adjust for bias due to unit non-response in surveys. Theory and simulations show that, to reduce bias effectively without increasing variance, a covariate that is used for non-response weighting adjustment needs to be highly associated with both the response indicator and the survey outcome variable. In practice, these requirements pose a challenge that is often overlooked, because those covariates are often not observed or may not exist. Surveys have recently begun to collect supplementary data, such as interviewer observations and other proxy measures of key survey outcome variables. To the extent that these auxiliary variables are highly correlated with the actual outcomes, these variables are promising candidates for non-response adjustment. In the present study, we examine traditional covariates and new auxiliary variables for the National Survey of Family Growth, the Medical Expenditure Panel Survey, the American National Election Survey, the European Social Surveys and the University of Michigan Transportation Research Institute survey. We provide empirical estimates of the association between proxy measures and response to the survey request as well as the actual survey outcome variables. We also compare unweighted and weighted estimates under various non-response models. Our results from multiple surveys with multiple recruitment protocols from multiple organizations on multiple topics show the difficulty of finding suitable covariates for non-response adjustment and the need to improve the quality of auxiliary data.

Survey agencies have started to use interviewer observations collected on all sample units to adjust survey estimates for non-response. Ideally, these observations should be related to both response indicators and key survey variables. However, these observations are typically judgements that are made by the interviewers, making them potentially prone to measurement error. Presenting analyses of data from the National Survey of Family Growth in the USA, this study examines the quality and utility of these interviewer observations and considers the implications of measurement errors in these observations for the effectiveness of non-response adjustments.

BACKGROUND Understanding cognitive decline trajectories is crucial for dementia prevention, as many cases go undetected. Identifying participation biases in such studies is essential for data validity. METHODS We examined non‐participation correlates in the Healthy Cognitive Ageing Project (HCAP), a sub‐study of the English Longitudinal Study of Ageing (ELSA). We compared sociodemographic and health characteristics of invited, interviewed, and non‐interviewed individuals, and assessed the impact of sample weights. RESULTS Of 1778 ELSA members invited in 2018, 1273 (72%) participated. Participants were similar to the invited sample in sociodemographics but were younger, had fewer daily living difficulties, and had better cognition. Non‐participation was linked to difficulties in daily living (odds ratio 1.78), dementia (1.55), and psychiatric conditions (1.34). Weighted analyses highlighted differences in disability and cognition. DISCUSSION Non‐participation in cognitive studies is not random, lowering response and retention rates, and requiring adjustments to data analysis beyond the use of weights. Highlights We compared the sociodemographics of invited, interviewed, and non‐interviewed individuals. We used sample weights to assess differences in participants' characteristics. We found non‐participation linked to daily living difficulties, dementia, and psychiatric conditions.

Objectives Ecological momentary assessment (EMA) has seen an explosion in popularity in recent years; however, an improved understanding of how to minimise (selective) non‐adherence is needed. Methods We examined a range of respondent characteristics predictors of adherence (defined as the number of EMA surveys completed) in the D2M EMA study. Participants were a sample of n = 255 individuals drawn from the longitudinal z‐proso cohort who completed up to 4 EMA surveys per day for a period of 2 weeks. Results In unadjusted analyses, lower moral shame, lower self‐control, lower levels of self‐injury, and higher levels of aggression, tobacco use, psychopathy, and delinquency were associated with lower adherence. In fully adjusted analyses with predictors selected using lasso, only alcohol use was related to adherence: beer and alcopops to higher adherence and spirits to lower adherence. Conclusions These findings provide potential insights into some of the psychological mechanisms that may underlie adherence in EMA. They also point to respondent characteristics for which additional or tailored efforts may be needed to promote adherence.

Non-response is a common source of error in many surveys. Because surveys often are costly instruments, quality-cost trade-offs play a continuing role in the design and analysis of surveys. The advances of telephone, computers, and Internet all had and still have considerable impact on the design of surveys. Recently, a strong focus on methods for survey data collection monitoring and tailoring has emerged as a new paradigm to efficiently reduce non-response error. Paradata and adaptive survey designs are key words in these new developments. Prerequisites to evaluating, comparing, monitoring, and improving quality of survey response are a conceptual framework for representative survey response, indicators to measure deviations thereof, and indicators to identify subpopulations that need increased effort. In this paper, we present an overview of representativeness indicators or R-indicators that are fit for these purposes. We give several examples and provide guidelines for their use in practice. La non-réponse est une source d'erreur importante dans de nombreuses enquêtes. Étant donné que les enquêtes sont souvent des opérations coûteuses, le compromis entre qualité et coût est omniprésent dans leur conception aussi bien que dans leur analyse. Les progrès du téléphone, des ordinateurs et d'internet tous ont eu, et ont encore, un impact considérable sur la conception des enquêtes. Récemment, l'accent a été mis sur les méthodes de collecte de données d'enquêtes de surveillance et l'adaptation est apparue comme un nouveau paradigme réduisant de façon efficace les erreurs liées à la non-réponse. «Paradonnées» (paradata) et plans de sondage adaptatifs sont les mots-clés de ces nouveaux développements. Les conditions préalables à l'évaluation, à la comparaison, à la surveillance et à l'amélioration de la qualité de la réponse du sondage sont un cadre conceptuel pour l'étude de la représentativité des résultats d'enquêtes et de leurs mesures de déviation, ainsi que pour l'identification des sous-populations requérant un effort accru. Dans cet article, nous présentons un aperçu des indicateurs de représentativité ou R-indicateurs qui sont propres à ces fins. Nous donnons plusieurs exemples, et des lignes directrices pour leur mise en pratique.

Non-response is unavoidable in longitudinal surveys. The consequences are lower statistical power and the potential for bias. We implemented a systematic data-driven approach to identify predictors of non-response in the National Child Development Study (NCDS; 1958 British birth cohort). Such variables can help make the missing at random assumption more plausible, which has implications for the handling of missing data We identified predictors of non-response using data from the 11 sweeps (birth to age 55) of the NCDS (n = 17,415), employing parametric regressions and the LASSO for variable selection. Disadvantaged socio-economic background in childhood, worse mental health and lower cognitive ability in early life, and lack of civic and social participation in adulthood were consistently associated with non-response. Using this information, along with other data from NCDS, we were able to replicate the “population distribution” of educational attainment and marital status (derived from external data), and the original distributions of key early life characteristics. The identified predictors of non-response have the potential to improve the plausibility of the missing at random assumption. They can be straightforwardly used as “auxiliary variables” in analyses with principled methods to reduce bias due to missing data.

The paper systematically reviews existing literature on the relationship between the level of effort to recruit a sampled person and the measurement quality of survey data. Hypotheses proposed for this relationship are reviewed. Empirical findings for the relationship between level of effort as measured by paradata (the number of follow-up attempts, refusal conversion and time in the field) and question-specific item non-response rates, aggregate measures of item non-response rates, response accuracy and various measurement errors on attitudinal questions are examined through a qualitative review.