A5021612023- Survey Methodology and Nonresponse
- Urban, Neighborhood, and Segregation Studies
- Health disparities and outcomes
- Gender, Labor, and Family Dynamics
- COVID-19 Pandemic Impacts
- Survey Sampling and Estimation Techniques
- Focus Groups and Qualitative Methods
- Behavioral Health and Interventions
- Social Power and Status Dynamics
- Social Capital and Networks
- COVID-19 epidemiological studies
- Social Policy and Reform Studies
- Healthcare Policy and Management
- Employment and Welfare Studies
- demographic modeling and climate adaptation
- Experimental Behavioral Economics Studies
- Financial Literacy, Pension, Retirement Analysis
- Labor market dynamics and wage inequality
- Economic and Environmental Valuation
- Statistical Methods and Bayesian Inference
- Mobile Crowdsensing and Crowdsourcing
- Human Mobility and Location-Based Analysis
- Homelessness and Social Issues
- Social and Intergroup Psychology
- Social Media and Politics
Institute for Social and Economic Research
2008-2024
University of Essex
2013-2024
Northrop Grumman (Germany)
2023
European University Institute
2021
U.S. National Science Foundation
2014
University of Maryland, College Park
2014
University of Nebraska–Lincoln
2014
Institut für Arbeitsmarkt und Berufsforschung
2014
Ludwig-Maximilians-Universität München
2014
Economic and Social Research Council
2008
Summary This paper discusses the challenges in assessing effects of mixed modes on measurement. We briefly review theories about why different data collection can lead to differences survey responses and statistical methods typically used assess mode effects. then discuss challenges, including which are identified, how test for effects, whether these would affect substantive conclusions. The issues raised illustrated with examples from European Social Survey, is conducting a programme...
Abstract Most genome-wide association studies are based on samples of European descent. We assess whether the genetic determinants blood lipids, a major cardiovascular risk factor, shared across populations. Genetic correlations for lipids between European-ancestry and Asian cohorts not significantly different from 1. A score LDL-cholesterol-associated loci has consistent effects serum levels in UK, Uganda Greece ( r = 0.23–0.28, p < 1.9 × 10 −14 ). Overall, there is evidence...
To measure what determines people’s attitudes, definitions, or decisions, surveys increasingly ask respondents to judge vignettes. A vignette typically describes a hypothetical situation object as having various attributes (dimensions). In factorial surveys, the values (levels) of dimensions are experimentally varied, so that their impact on respondents’ judgments can be estimated. Drawing literature in cognitive psychology and survey methodology, we examine two research questions: Does...
Journal Article Assessing the Mechanisms of Misreporting to Filter Questions in Surveys Get access Stephanie Eckman, Eckman * is a senior researcher at Institute for Employment Research (IAB) Nuremberg, Germany. Frauke Kreuter professor Joint Program Survey Methodology University Maryland, College Park, MD, USA; head Statistical Methods Department Germany, with affiliation Ludwig Maximilian Munich; and statistics methodology Mannheim University, Mannheim, Antje Kirchner postdoctoral research...
Abstract Obesity is a genetically heterogeneous disorder. Using targeted and whole-exome sequencing, we studied 32 human 87 rodent obesity genes in 2,548 severely obese children 1,117 controls. We identified 52 variants contributing to 2% of cases including multiple novel GNAS , which were sometimes found with accelerated growth rather than short stature as described previously. Nominally significant associations for rare functional BBS1 BBS9 MKKS CLOCK ANGPTL6 . The p.S284X variant drives...
Using new data from the Understanding Society: COVID 19 survey collected in April 2020, we show how aggregate shock caused by pandemic affects individuals across distribution. The collects existing members of Society panel who have been followed for up to 10 years. society is based on probability samples and Covid19 Survey carefully constructed support valid population inferences. Further allows comparisons with a pre-pandemic baseline. We document translates into different economic shocks...
The impact of the pandemic on UK labour market has been extremely heterogeneous across occupations and industries. Using novel data job search, we document how individuals adjust their search in response to changing employment patterns industries UK. We observe that workers changed direction favour expanding as developed. However, non-employed are more attached previous with low education likely target declining occupations. also from making fewer transitions than those who start...
Summary We analyse patterns of consent and bias in the context a large general household survey, ‘Improving survey measurement income employment’ also addressing issues that arise when there are multiple questions. A multivariate probit regression model for four binary outcomes with two incidental truncations is used. show biases to data linkage benefit tax credit administrative records held by Department Work Pensions, wage employment employers. There respondents’ willingness ability supply...
We asked members of the Understanding Society Innovation Panel about their willingness to participate in various data collection tasks on mobile devices. find that stated varies considerably depending type activity involved: respondents are less willing involve downloading and installing an app, or where collected passively. Stated also between smartphones tablets, types respondents: who report higher concerns security with technologies those use devices intensively tasks.
There are considerable cost and timeliness advantages associated with web interviewing, compared to interviewer administration. However, surveys do not perform well in terms of coverage participation. To harness the strengths both modes, existing probability-based interviewer-administered therefore being pushed consider a mixed mode approach, including web. We assess effect introducing interviewing as part mixed-mode design context an longitudinal survey which sample members have previously...
This paper examines non-response in a mobile app study designed to collect expenditure data. We invited 2,383 members of the nationally representative Understanding Society Innovation Panel Great Britain download an record their spending on goods and services: participants were asked scan receipts or report directly every day for month. examine participation at different stages process. further use data from prior wave panel prevalence potential barriers participation, including access,...
This chapter contains sections titled: Introduction Dependent Interviewing – What and Why? Design Options their Effects Empirical Evidence of on Data Quality Across Surveys Open Issues Acknowledgements References
This paper examines the role of interviewers' experience, attitudes, personality traits and inter-personal skills in determining survey co-operation, conditional on contact. We take perspective that these characteristics influence behaviour hence doorstep interaction between interviewer sample member. Previous studies association co-operation have not directly addressed most been based small samples interviewers. use a large 842 face-to-face interviewers working for major institute analyse...
Summary We assess measurement error in panel survey reports of social security benefit receipt, drawing on a unique validation study. Our aims are threefold. First, we quantify the incidence errors (under- and over-reporting). Second, extent to which this varies according questioning method that is used. Specifically, dependent interviewing has been proposed as way reduce under-reporting some circumstances. compare two versions with traditional independent an experimental design. Third,...
Using new data from the Understanding Society: COVID 19 survey collected in April 2020, we show how aggregate shock caused by pandemic affects individuals across distribution.The collects existing members of Society panel who have been followed for up to 10 years.Understanding society is based on probability samples and Covid19Survey carefully constructed support valid population inferences.Further allows comparisons with a pre-pandemic baseline.We document translates into different economic...
Linkage of household survey responses with administrative data is increasingly on the agenda. Unique individual identifiers have clear benefits for making linkages but are also subject to problems item non-response and measurement error. Our experimental study that linked UK government agency records tax credits elucidates this trade-off. We compare five linkage criteria: one based a respon-dent-supplied National Insurance Number (NINO) other four using different combinations sex, name,...
Offering participants in mobile app studies personalized feedback on the data they report seems an obvious thing to do: Participants might expect provide given their experiences with commercial apps, motivate more people participate study, and be motivated accurate so that is useful them. However, lead change behavior being measured app, costly implement, also constrains other design decisions for collection. In this article, we experimental study tested effects of providing a 1-month...
The work of Smyth, Dillman, Christian, and Stern (2006) Dillman (2008) compares “yes/no” questions to “check all that apply” questions. They conclude the format is preferable as it reflects deeper processing survey Smyth et al. found performed similarly across telephone web modes. In this paper we replicate their research extend by including a comparison with face-to-face in addition using probability samples general adult population. A cognitive interviewing follow-up was used explore...
Using panel data on micro enterprises from Peru we find evidence suggesting that firm dynamics explain “formality,” where formality is recast as the firm’s decision to participate in societal institutions. The results suggest differences unobservable factors, such entrepreneurial ability, contribute largely growth rates, survival chances, and participation. After controlling for unobserved heterogeneity, probability of participation increases with size but not years business. Changes status...