Assessing the Quality of Survey Data: (Research Methods for Social Scientists)

This is a book for any researcher using any kind of survey data. It introduces the latest methods of assessing the quality and validity of such data by providing new ways of interpreting variation and measuring error. By practically and accessibly demonstrating these techniques, especially those derived from Multiple Correspondence Analysis, the authors develop screening procedures to search for variation in observed responses that do not correspond with actual differences between respondents. Using well-known international data sets, the authors exemplify how to detect all manner of non-substantive variation having sources such as a variety of response styles including acquiescence, respondents' failure to understand questions, inadequate field work standards, interview fatigue, and even the manufacture of (partly) faked interviews.

Table of Contents:
Conceptualizing Data Quality: Respondent Attributes, Study Architecture, and Institutional Practices Conceptualizing Response Quality Study Architecture Institutional Quality Control Practices Data Screening Methodology Chapter Outline Empirical Findings on Quality and Comparability of Survey Data Response Quality Approaches to Detecting Systematic Response Errors Questionnaire Architecture Cognitive Maps in Cross-Cultural Perspective Conclusion Statistical Techniques for Data Screening Principal Component Analysis Categorical Principal Component Analysis Multiple Correspondence Analysis Conclusion Institutional Quality Control Practices Detecting Procedural Deficiencies Data Duplication Detecting Faked and Partly Faked Interviews Data Entry Errors Conclusion Substantive or Methodology-Induced Factors? A Comparison of PCA, CatPCA and MCA Solutions Descriptive Analysis of Personal Feelings Domain Rotation and Structure of Data Conclusion Item Difficulty and Response Quality Descriptive Analysis of Political Efficacy Domain Detecting Patterns with Subset Multiple Correspondence Analysis Moderator Effects Conclusion Questionnaire Architecture Fatigue Effect Question Order Effects Measuring Data Quality: The Dirty Data Index Conclusion Cognitive Competencies and Response Quality Data and Measures Response Quality, Task Simplification and Complexity of Cognitive Maps Conclusion Conclusion

About the Author :
Jörg Blasius is a professor of Sociology at the Institute for Political Science and Sociology, University of Bonn, Germany. His research interests are mainly focused on explorative data analysis, especially correspondence analysis and related methods, data collection methods, sociology of lifestyles, and urban sociology. He is a coeditor of the SAGE Series “Survey Research Methods in the Social Sciences.” Together with Michael Greenacre (University Pompeu Fabra, Barcelona), he founded Carme (Correspondence Analysis and Related Methods Network, see www.carme-n.org). From 1998 to 2016, he belonged to the Board of RC33 (Research Committee on Logic and Methodology in Sociology) of the ISA (International Sociological Association), from 2006 to 2010 he served as president. Website: https://www.politik-soziologie.uni-bonn.de/de/personal/Prof.-Dr.-Joerg-Blasius

Review :
This is an innovative book. Blasius and Thiessen show how careful data-analysis can uncover defects in survey data, without having recourse to meta-data or other extra information. This is good news for researchers who work with existing data sets and wish to assess their quality Joop Hox Professor of social science methodology, Utrecht University ′This illuminating and innovative book on the quality of survey data focuses on screening procedures that should be conducted prior to assessing substantive relations. Numerous tables and visual displays based on appropriate analyses show convincing examples of procedural deficiencies, data duplicates, and faked interview, and unusual patterns in well known international datasets. Blasius and Thiessen discuss openly what is mostly covered in survey reporting, and they show ways to improve the reliability of conclusions based on survey data. A must for survey practitioners and users Jaak Billiet Emeritus professor in social methodology, University of Leuven ′I hope that many social science researchers will read Jörg Blasius and Victor Thiessen′s book and realize the importance of the lesson it provides, which is that many of our data sets contain serious errors which may lead to wrong conclusions if not wrong theories. Applying the suggested tests can prevent this. Willem Saris Director of RECSM, Universitat Pompeu Fabra, Barcelona This is an important, groundbreaking analysis of survey data quality that serves as an indispensable vade mecum for anyone engaged in gathering, analysing or utilising survey data. Clearly quality is not always what is appears to be... Assessing the Quality of Survey Data... addresses this issue in far more detail than any other work known to this reviewer. Maryam Nazari and G. E. Gorman Online Information Review Assessing the Quality of Survey Data has been written for all researchers who want to be good data detectives... This book has some considerable strengths. It really got me to reflect on the assumptions I had made about data sets I had handled. It highlighted how relatively easy it is to spot data issues early on in analysis. It also made me think of response style challenges to be more than a survey design/sampling issues and to include much more data screening. Although I won’t be setting up my own detective agency, I have certainly picked up some sleuthing tips. Catherine Owens SR: Reviews