Advances in Longitudinal Survey Methodology

Advances in Longitudinal Survey Methodology

by Peter Lynn
Released March 2021
Publisher(s): Wiley
ISBN: 9781119376934

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Advances in Longitudinal Survey Methodology

Explore an up-to-date overview of best practices in the implementation of longitudinal surveys from leading experts in the field of survey methodology

Advances in Longitudinal Survey Methodology delivers a thorough review of the most current knowledge in the implementation of longitudinal surveys. The book provides a comprehensive overview of the many advances that have been made in the field of longitudinal survey methodology over the past fifteen years, as well as extending the topic coverage of the earlier volume, “Methodology of Longitudinal Surveys”, published in 2009. This new edited volume covers subjects like dependent interviewing, interviewer effects, panel conditioning, rotation group bias, measurement of cognition, and weighting.

New chapters discussing the recent shift to mixed-mode data collection and obtaining respondents’ consent to data linkage add to the book’s relevance to students and social scientists seeking to understand modern challenges facing data collectors today. Readers will also benefit from the inclusion of:

  • A thorough introduction to refreshment sampling for longitudinal surveys, including consideration of principles, sampling frame, sample design, questionnaire design, and frequency
  • An exploration of the collection of biomarker data in longitudinal surveys, including detailed measurements of ill health, biological pathways, and genetics in longitudinal studies
  • An examination of innovations in participant engagement and tracking in longitudinal surveys, including current practices and new evidence on internet and social media for participant engagement.

    • An invaluable source for post-graduate students, professors, and researchers in the field of survey methodology, Advances in Longitudinal Survey Methodology will also earn a place in the libraries of anyone who regularly works with or conducts longitudinal surveys and requires a one-stop reference for the latest developments and findings in the field.

    Table of contents

    1. Cover
    2. Table of Contents
    3. Series Title Page
    4. Title Page
    5. Copyright Page
    6. List of Contributors
    7. Preface
    8. About the Companion Website
    9. 1 Refreshment Sampling for Longitudinal Surveys
      1. 1.1 Introduction
      2. 1.2 Principles
      3. 1.3 Sampling
        1. 1.3.1 Sampling Frame
        2. 1.3.2 Screening
        3. 1.3.3 Sample Design
        4. 1.3.4 Questionnaire Design
        5. 1.3.5 Frequency
      4. 1.4 Recruitment
      5. 1.5 Data Integration
      6. 1.6 Weighting
      7. 1.7 Impact on Analysis
      8. 1.8 Conclusions
      9. References
      10. Notes
    10. 2 Collecting Biomarker Data in Longitudinal Surveys
      1. 2.1 Introduction
      2. 2.2 What Are Biomarkers, and Why Are They of Value?
        1. 2.2.1 Detailed Measurements of Ill Health
        2. 2.2.2 Biological Pathways
        3. 2.2.3 Genetics in Longitudinal Studies
      3. 2.3 Approaches to Collecting Biomarker Data in Longitudinal Studies
        1. 2.3.1 Consistency and Relevance of Measures Over Time
        2. 2.3.2 Panel Conditioning and Feedback
        3. 2.3.3 Choices of When and Who to Ask for Sensitive or Invasive Measures
        4. 2.3.4 Cost
      4. 2.4 The Future
      5. References
    11. 3 Innovations in Participant Engagement and Tracking in Longitudinal Surveys
      1. 3.1 Introduction and Background
      2. 3.2 Literature Review
      3. 3.3 Current Practice
      4. 3.4 New Evidence on Internet and Social Media for Participant Engagement
        1. 3.4.1 Background
        2. 3.4.2 Findings
          1. 3.4.2.1 MCS
          2. 3.4.2.2 Next Steps
        3. 3.4.3 Summary and Conclusions
      5. 3.5 New Evidence on Internet and Social Media for Tracking
        1. 3.5.1 Background
        2. 3.5.2 Findings
        3. 3.5.3 Summary and Conclusions
      6. 3.6 New Evidence on Administrative Data for Tracking
        1. 3.6.1 Background
        2. 3.6.2 Findings
        3. 3.6.3 Summary and Conclusions
      7. 3.7 Conclusion
      8. Acknowledgements
      9. References
      10. 3.A List of Studies that Responded to the Survey
    12. 4 Effects on Panel Attrition and Fieldwork Outcomes from Selection for a Supplemental Study: Evidence from the Panel Study of Income Dynamics
      1. 4.1 Introduction
      2. 4.2 Conceptual Framework
      3. 4.3 Previous Research
      4. 4.4 Data and Methods
      5. 4.5 Results
      6. 4.6 Conclusions
      7. Acknowledgements
      8. References
    13. 5 The Effects of Biological Data Collection in Longitudinal Surveys on Subsequent Wave Cooperation
      1. 5.1 Introduction
      2. 5.2 Literature Review
      3. 5.3 Biological Data Collection and Subsequent Cooperation: Research Questions
      4. 5.4 Data
      5. 5.5 Modelling Steps
      6. 5.6 Results
      7. 5.7 Discussion and Conclusion
      8. 5.8 Implications for Survey Researchers
      9. References
      10. Notes
    14. 6 Understanding Data Linkage Consent in Longitudinal Surveys
      1. 6.1 Introduction
      2. 6.2 Quantitative Research: Consistency of Consent and Effect of Mode of Data Collection
        1. 6.2.1 Data and Methods
        2. 6.2.2 Results
          1. 6.2.2.1 How Consistent Are Respondents about Giving Consent to Data Linkage between Topics?
          2. 6.2.2.2 How Consistent Are Respondents about Giving Consent to Data Linkage over Time?
          3. 6.2.2.3 Does Consistency over Time Vary between Domains?
          4. 6.2.2.4 What Is the Effect of Survey Mode on Consent?
      3. 6.3 Qualitative Research: How Do Respondents Decide Whether to Give Consent to Linkage?
        1. 6.3.1 Methods
        2. 6.3.2 Results
          1. 6.3.2.1 How Do Participants Interpret Consent Questions?
          2. 6.3.2.2 What Do Participants Think Are the Implications of Giving Consent to Linkage?
          3. 6.3.2.3 What Influences the Participant's Decision Whether or Not to Give Consent?
          4. 6.3.2.4 How Does the Survey Mode Influence the Decision to Consent?
          5. 6.3.2.5 Why Do Participants Change their Consent Decision over Time?
      4. 6.4 Discussion
      5. Acknowledgements
      6. References
      7. Notes
    15. 7 Determinants of Consent to Administrative Records Linkage in Longitudinal Surveys: Evidence from Next Steps
      1. 7.1 Introduction
      2. 7.2 Literature Review
      3. 7.3 Data and Methods
        1. 7.3.1 About the Study
        2. 7.3.2 Consents Sought and Consent Procedure
        3. 7.3.3 Analytic Sample
        4. 7.3.4 Methods
      4. 7.4 Results
        1. 7.4.1 Consent Rates
        2. 7.4.2 Regression Models
          1. 7.4.2.1 Concepts and Variables
          2. 7.4.2.2 Characteristics Related to All or Most Consent Domains
          3. 7.4.2.3 National Health Service (NHS) Records
          4. 7.4.2.4 Police National Computer (PNC) Criminal Records
          5. 7.4.2.5 Education Records
            1. 7.4.2.5.1 Characteristics Related to Consent to All Education Records
            2. 7.4.2.5.2 Department for Education (DfE) and Higher Education Statistics Agency (HESA) records
            3. 7.4.2.5.3 Universities and College Admissions Service (UCAS) records
            4. 7.4.2.5.4 Student Loans Company (SLC) Records
          6. 7.4.2.6 Economic Records
            1. 7.4.2.6.1 Characteristics Related to Consent to All Economic Records
            2. 7.4.2.6.2 Her Majesty's Revenue and Customs (HMRC) Records
            3. 7.4.2.6.3 Department for Work and Pensions (DWP) Records
            4. 7.4.2.6.4 National Insurance Number (NINO)
      5. 7.5 Discussion
        1. 7.5.1 Summary of Results
        2. 7.5.2 Methodological Considerations and Limitations
        3. 7.5.3 Practical Implications
      6. References
      7. Notes
    16. 8 Consent to Data Linkage: Experimental Evidence from an Online Panel
      1. 8.1 Introduction
      2. 8.2 Background
        1. 8.2.1 Experimental Studies of Data Linkage Consent in Longitudinal Surveys
      3. 8.3 Research Questions
      4. 8.4 Method
        1. 8.4.1 Data
        2. 8.4.2 Study 1: Attrition Following Data Linkage Consent
        3. 8.4.3 Study 2: Testing the Effect of Type and Length of Data Linkage Consent Questions
      5. 8.5 Results
        1. 8.5.1 Do Requests for Data Linkage Consent Affect Response Rates in Subsequent Waves? (RQ1)
        2. 8.5.2 Do Consent Rates Depend on Type of Data Linkage Requested? (RQ2a)
        3. 8.5.3 Do Consent Rates Depend on Survey Mode? (RQ2b)
        4. 8.5.4 Do Consent Rates Depend on the Length of the Request? (RQ2c)
        5. 8.5.5 Effects on Understanding of the Data Linkage Process (RQ3)
        6. 8.5.6 Effects on Perceptions of the Risk of Data Linkage (RQ4)
      6. 8.6 Discussion
      7. References
      8. Notes
    17. 9 Mixing Modes in Household Panel Surveys: Recent Developments and New Findings
      1. 9.1 Introduction
      2. 9.2 The Challenges of Mixing Modes in Household Panel Surveys
      3. 9.3 Current Experiences with Mixing Modes in Longitudinal Household Panels
        1. 9.3.1 The German Socio‐Economic Panel (SOEP)
        2. 9.3.2 The Household, Income, and Labour Dynamics in Australia (HILDA) Survey
        3. 9.3.3 The Panel Study of Income Dynamics (PSID)
        4. 9.3.4 The UK Household Longitudinal Study (UKHLS)
        5. 9.3.5 The Korean Labour and Income Panel Study (KLIPS)
        6. 9.3.6 The Swiss Household Panel (SHP)
      4. 9.4 The Mixed‐Mode Pilot of the Swiss Household Panel Study
        1. 9.4.1 Design of the SHP Pilot
        2. 9.4.2 Results of the First Wave
          1. 9.4.2.1 Overall Response Rates in the Three Groups
          2. 9.4.2.2 Use of Different Modes in the Three Groups
          3. 9.4.2.3 Household Nonresponse in the Three Groups
          4. 9.4.2.4 Individual Nonresponse in the Three Groups
      5. 9.5 Conclusion
      6. References
      7. Notes
    18. 10 Estimating the Measurement Effects of Mixed Modes in Longitudinal Studies: Current Practice and Issues
      1. 10.1 Introduction
      2. 10.2 Types of Mixed‐Mode Designs
      3. 10.3 Mode Effects and Longitudinal Data
        1. 10.3.1 Estimating Change from Mixed‐Mode Longitudinal Survey Data
        2. 10.3.2 General Concepts in the Investigation of Mode Effects
        3. 10.3.3 Mode Effects on Measurement in Longitudinal Data: Literature Review
      4. 10.4 Methods for Estimating Mode Effects on Measurement in Longitudinal Studies
      5. 10.5 Using Structural Equation Modelling to Investigate Mode Differences in Measurement
      6. 10.6 Conclusion
      7. Acknowledgement
      8. References
      9. Notes
    19. 11 Measuring Cognition in a Multi‐Mode Context
      1. 11.1 Introduction
      2. 11.2 Motivation and Previous Literature
        1. 11.2.1 Measurement of Cognition in Surveys
        2. 11.2.2 Mode Effects and Survey Response
        3. 11.2.3 Cognition in a Multi‐Mode Context
        4. 11.2.4 Existing Mode Comparisons of Cognitive Ability
      3. 11.3 Data and Methods
        1. 11.3.1 Data Source
        2. 11.3.2 Analytic Sample
        3. 11.3.3 Administration of Cognitive Tests
        4. 11.3.4 Methods
          1. 11.3.4.1 Item Missing Data
          2. 11.3.4.2 Completion Time
          3. 11.3.4.3 Overall Differences in Scores
          4. 11.3.4.4 Correlations Between Measures
          5. 11.3.4.5 Trajectories over Time
          6. 11.3.4.6 Models Predicting Cognition as an Outcome
      4. 11.4 Results
        1. 11.4.1 Item‐Missing Data
        2. 11.4.2 Completion Time
        3. 11.4.3 Differences in Mean Scores
        4. 11.4.4 Correlations Between Measures
        5. 11.4.5 Trajectories over Time
        6. 11.4.6 Substantive Models
      5. 11.5 Discussion
      6. Acknowledgements
      7. References
      8. Notes
    20. 12 Panel Conditioning: Types, Causes, and Empirical Evidence of What We Know So Far
      1. 12.1 Introduction
      2. 12.2 Methods for Studying Panel Conditioning
      3. 12.3 Mechanisms of Panel Conditioning
        1. 12.3.1 Survey Response Process and the Effects of Repeated Interviewing
        2. 12.3.2 Reflection/Cognitive Stimulus
        3. 12.3.3 Empirical Evidence of Reflection/Cognitive Stimulus
          1. 12.3.3.1 Changes in Attitudes Due to Reflection
          2. 12.3.3.2 Changes in (Self‐Reported) Behaviour Due to Reflection
          3. 12.3.3.3 Changes in Knowledge Due to Reflection
        4. 12.3.4 Social Desirability Reduction
        5. 12.3.5 Empirical Evidence of Social Desirability Effects
        6. 12.3.6 Satisficing
        7. 12.3.7 Empirical Evidence of Satisficing
          1. 12.3.7.1 Misreporting to Filter Questions as a Conditioning Effect Due to Satisficing
          2. 12.3.7.2 Misreporting to More Complex Filter (Looping) Questions
          3. 12.3.7.3 Within‐Interview and Between‐Waves Conditioning in Filter Questions
      4. 12.4 Conclusion and Implications for Survey Practice
      5. References
      6. Notes
    21. 13 Interviewer Effects in Panel Surveys
      1. 13.1 Introduction
      2. 13.2 Motivation and State of Research
        1. 13.2.1 Sources of Interviewer‐Related Measurement Error
          1. 13.2.1.1 Interviewer Deviations
          2. 13.2.1.2 Social Desirability
          3. 13.2.1.3 Priming
        2. 13.2.2 Moderating Factors of Interviewer Effects
        3. 13.2.3 Interviewer Effects in Panel Surveys
        4. 13.2.4 Identifying Interviewer Effects
          1. 13.2.4.1 Interviewer Variance
          2. 13.2.4.2 Interviewer Bias
          3. 13.2.4.3 Using Panel Data to Identify Interviewer Effects
      3. 13.3 Data
        1. 13.3.1 The Socio‐Economic Panel
        2. 13.3.2 Variables
      4. 13.4 The Size and Direction of Interviewer Effects in Panels
        1. 13.4.1 Methods
        2. 13.4.2 Results
        3. 13.4.3 Effects on Precision
        4. 13.4.4 Effects on Validity
      5. 13.5 Dynamics of Interviewer Effects in Panels
        1. 13.5.1 Methods
        2. 13.5.2 Results
          1. 13.5.2.1 Interviewer Variance
          2. 13.5.2.2 Interviewer Bias
      6. 13.6 Summary and Discussion
      7. References
      8. Notes
    22. 14 Improving Survey Measurement of Household Finances: A Review of New Data Sources and Technologies
      1. 14.1 Introduction
        1. 14.1.1 Why Is Good Financial Data Important for Longitudinal Surveys?
        2. 14.1.2 Why New Data Sources and Technologies for Longitudinal Surveys?
        3. 14.1.3 How Can New Technologies Change the Measurement Landscape?
      2. 14.2 The Total Survey Error Framework
      3. 14.3 Review of New Data Sources and Technologies
        1. 14.3.1 Financial Aggregators
        2. 14.3.2 Loyalty Card Data
        3. 14.3.3 Credit and Debit Card Data
        4. 14.3.4 Credit Rating Data
        5. 14.3.5 In‐Home Scanning of Barcodes
        6. 14.3.6 Scanning of Receipts
        7. 14.3.7 Mobile Applications and Expenditure Diaries
      4. 14.4 New Data Sources and Technologies and TSE
        1. 14.4.1 Errors of Representation
          1. 14.4.1.1 Coverage Error
          2. 14.4.1.2 Non‐Participation Error
        2. 14.4.2 Measurement Error
          1. 14.4.2.1 Specification Error
          2. 14.4.2.2 Missing or Duplicate Items/Episodes
          3. 14.4.2.3 Data Capture Error
          4. 14.4.2.4 Processing or Coding Error
          5. 14.4.2.5 Conditioning Error
      5. 14.5 Challenges and Opportunities
      6. Acknowledgements
      7. References
    23. 15 How to Pop the Question? Interviewer and Respondent Behaviours When Measuring Change with Proactive Dependent Interviewing
      1. 15.1 Introduction
      2. 15.2 Background
      3. 15.3 Data
      4. 15.4 Behaviour Coding Interviewer and Respondent Interactions
      5. 15.5 Methods
      6. 15.6 Results
        1. 15.6.1 Does the DI Wording Affect how Interviewers and Respondents Behave? (RQ1)
        2. 15.6.2 Does the Wording of DI Questions Affect the Sequences of Interviewer and Respondent Interactions? (RQ2)
        3. 15.6.3 Which Interviewer Behaviours Lead to Respondents Giving Codeable Answers? (RQ3)
        4. 15.6.4 Are the Different Rates of Change Measured with Different DI Wordings Explained by Differences in I and R Behaviours? (RQ4)
      7. 15.7 Conclusion
      8. Acknowledgements
      9. References
      10. 15.A IP3 Stems of Experimental Dependent Interviewing Questions
      11. 15.B IP7 Stems of Experimental Dependent Interviewing Questions
      12. 15.C Behaviour Coding Frame
      13. Note
    24. 16 Assessing Discontinuities and Rotation Group Bias in Rotating Panel Designs
      1. 16.1 Introduction
      2. 16.2 Methods for Quantifying Discontinuities
      3. 16.3 Time Series Models for Rotating Panel Designs
        1. 16.3.1 Rotating Panels and Rotation Group Bias
        2. 16.3.2 Structural Time Series Model for Rotating Panels
        3. 16.3.3 Fitting Structural Time Series Models
      4. 16.4 Time Series Models for Discontinuities in Rotating Panel Designs
        1. 16.4.1 Structural Time Series Model for Discontinuities
        2. 16.4.2 Parallel Run
        3. 16.4.3 Combining Information from a Parallel Run with the Intervention Model
        4. 16.4.4 Auxiliary Time Series
      5. 16.5 Examples
        1. 16.5.1 Redesigns in the Dutch LFS
        2. 16.5.2 Using a State Space Model to Assess Redesigns in the UK LFS
      6. 16.6 Discussion
      7. References
    25. 17 Proper Multiple Imputation of Clustered or Panel Data
      1. 17.1 Introduction
      2. 17.2 Missing Data Mechanism and Ignorability
      3. 17.3 Multiple Imputation (MI)
        1. 17.3.1 Theory and Basic Approaches
        2. 17.3.2 Single Versus Multiple Imputation
          1. 17.3.2.1 Unconditional Mean Imputation and Regression Imputation
          2. 17.3.2.2 Last Observation Carried Forward
          3. 17.3.2.3 Row‐and‐Column Imputation
      4. 17.4 Issues in the Longitudinal Context
        1. 17.4.1 Single‐Level Imputation
        2. 17.4.2 Multilevel Multiple Imputation
        3. 17.4.3 Interactions and Non‐Linear Associations
      5. 17.5 Discussion
      6. References
      7. Notes
    26. 18 Issues in Weighting for Longitudinal Surveys
      1. 18.1 Introduction: The Longitudinal Context
        1. 18.1.1 Dynamic Study Population
        2. 18.1.2 Wave Non‐Response Patterns
        3. 18.1.3 Auxiliary Variables
        4. 18.1.4 Longitudinal Surveys as a Multi‐Purpose Research Resource
        5. 18.1.5 Multiple Samples
      2. 18.2 Population Dynamics
        1. 18.2.1 Post‐Stratification
        2. 18.2.2 Population Entrants
        3. 18.2.3 Uncertain Eligibility
      3. 18.3 Sample Participation Dynamics
        1. 18.3.1 Subsets of Instrument Combinations
        2. 18.3.2 Weights for Each Pair of Instruments
        3. 18.3.3 Analysis‐Specific Weights
      4. 18.4 Combining Multiple Non‐Response Models
      5. 18.5 Discussion
      6. Acknowledgements
      7. References
      8. Note
    27. 19 Small‐Area Estimation of Cross‐Classified Gross Flows Using Longitudinal Survey Data
      1. 19.1 Introduction
      2. 19.2 Role of Model‐Assisted Estimation in Small Area Estimation
      3. 19.3 Data and Methods
        1. 19.3.1 Data
        2. 19.3.2 Estimate and Variance Comparisons
      4. 19.4 Estimating Gross Flows
      5. 19.5 Models
        1. 19.5.1 Generalised Logistic Fixed Effect Models
        2. 19.5.2 Fixed Effect Logistic Models for Estimating Gross Flows
        3. 19.5.3 Equivalence between Fixed‐Effect Logistic Regression and Log‐Linear Models
        4. 19.5.4 Weighted Estimation
        5. 19.5.5 Mixed‐Effect Logit Models for Gross Flows
        6. 19.5.6 Application to the Estimation of Gross Flows
      6. 19.6 Results
        1. 19.6.1 Goodness of Fit Tests for Fixed Effect Models
        2. 19.6.2 Fixed‐Effect Logit‐Based Estimation of Gross Flows
        3. 19.6.3 Mixed Effect Models
        4. 19.6.4 Comparison of Models through BRR Variance Estimation
      7. 19.7 Discussion
      8. Acknowledgements
      9. References
    28. 20 Nonparametric Estimation for Longitudinal Data with Informative Missingness
      1. 20.1 Introduction
      2. 20.2 Two NEE Estimators of Change
      3. 20.3 On the Bias of NEE
      4. 20.4 Variance Estimation
        1. 20.4.1 NEE (Expression 20.3)
        2. 20.4.2 NEE (Expression 20.6)
      5. 20.5 Simulation Study
        1. 20.5.1 Data
        2. 20.5.2 Response Probability Models
        3. 20.5.3 Simulation Set‐up
        4. 20.5.4 Results
      6. 20.6 Conclusions
      7. References
    29. Index
    30. WILEY END USER LICENSE AGREEMENT

    Product information

    • Title: Advances in Longitudinal Survey Methodology
    • Author(s): Peter Lynn
    • Release date: March 2021
    • Publisher(s): Wiley
    • ISBN: 9781119376934