Search Results

Summary and Conclusions

Roger Tourangeau, Frederick G. Conrad, and Mick P. Couper

in The Science of Web Surveys

In addition to reviewing the main findings and themes of the book, the final chapter grapples with a central issue in the design of mixed-mode surveys. Should researchers try to minimize differences ... More

In addition to reviewing the main findings and themes of the book, the final chapter grapples with a central issue in the design of mixed-mode surveys. Should researchers try to minimize differences across modes by avoiding mode-dependent features or should they try to take advantage of the strengths of each mode? These two approaches are sometimes called the unimodeand the best practicesapproaches, respectively. The chapter presents a mathematical model for mode effects. The model implies that when the purpose of the survey is to produce point estimates, particularly of factual phenomena, the best practices approach is generally most appropriate; however, when the point of the survey is to make comparisons across groups, especially for subjective phenomena, the unimode approach is generally the most appropriate. Finally, the chapter presents a list of recommendations for practice derived from the empirical findings discussed in the book.Less

Mode Differences: Dealing with Sensitive Topics

in The Total Survey Error Approach: A Guide to the New Science of Survey Research

Survey modes are not considered a type of survey error, probably because there is no objective standard against which results from different modes can be compared. Still, it is important to ... More

Survey modes are not considered a type of survey error, probably because there is no objective standard against which results from different modes can be compared. Still, it is important to understand the effects that the choice of survey mode can have. Several studies have explicitly compared different modes. Some of these studies were intended to determine whether it was safe to move from face to-face to telephone interviewing and more recently, whether it was safe to move from telephone to Internet surveys. Many studies check whether particular modes are better for dealing with sensitive topics. Additionally, some studies advocate using multiple modes, partly to overcome coverage problems that may be inherent in any single mode.Less

Surveying Employers and Individuals with Disabilities

William A. Erickson, Sarah von Schrader, and Sara VanLooy

in Disability and Employer Practices: Research across the Disciplines

This chapter examines survey research in order to provide an understanding of its strengths and limitations, presenting practical approaches and considerations specifically with regard to gathering ... More

This chapter examines survey research in order to provide an understanding of its strengths and limitations, presenting practical approaches and considerations specifically with regard to gathering information about employer practices and disability employment issues. It begins with a discussion of surveys as a primary data-collection approach for disability and employment data and discusses several possible types of survey informants for employer practices research, each of whom have access to different types of information and provide different perspectives. The chapter then provides an overview of some key considerations that can affect the generalizability of results, including sampling approaches, survey administration mode, and strategies to increase response rate. Of course, as the perspectives of individuals with disabilities may be the focus of a survey, special considerations in surveying individuals with disabilities are discussed.Less

Survey Modes: Responses to Emerging Technologies

in The Total Survey Error Approach: A Guide to the New Science of Survey Research

Two basic distinctions between survey modes are developed in this chapter, after which some related research approaches are discussed. Computer-assisted survey information collection and Internet ... More

Two basic distinctions between survey modes are developed in this chapter, after which some related research approaches are discussed. Computer-assisted survey information collection and Internet surveys are described in detail. There are two important distinctions to make about survey modes. One is how personal they are in terms of the extent of interviewer involvement: whether the survey is self-administered or interviewer administered. Face-to-face and telephone surveys are generally interviewer administered. Face-to-face interviews are usually in the respondents' natural surroundings, as when interviewers go to people's homes or offices. Skillful interviewers can usually get a high response rate and can conduct very high-quality interviews. It is harder to exercise quality control because these interviews are usually not monitored, though even monitoring is possible with modern recording technology. The response rate and interview quality are generally lower in phone interviews. Telephone surveys can be conducted out of a central telephone facility (a “calling center”), which improves quality control since a supervisor can oversee the process. The data can be collected much faster than with mail surveys or face-to-face interviews, which is important to clients who want daily updates.Less

Asking Households about Expenditures: What Have We Learned?

Thomas F. Crossley and Joachim K. Winter

in Improving the Measurement of Consumer Expenditures

There is mounting evidence of problems with the household budget surveys conducted by national statistical agencies in many countries. When designing household surveys, including surveys that measure ... More

There is mounting evidence of problems with the household budget surveys conducted by national statistical agencies in many countries. When designing household surveys, including surveys that measure consumption expenditure, numerous choices need to be made. Which survey mode should be used? Do recall questions or diaries provide more reliable expenditure data? How should the concept of a household be defined? How should the length of the recall period, the level of aggregation of expenditure items, and the response format be chosen? How are responses affected by incentives? Can computer-assisted surveys be used to reduce or correct response error in real time? In this chapter, we provide a selective review of the literature on these questions. We also suggest some promising directions for future research.Less

Patient experience surveys

Chris Graham and Penny Woods

in Understanding and Using Health Experiences: Improving patient care

Surveys of patients’ experiences are increasingly commonplace in healthcare. They are used to address a range of purposes, from driving quality improvements and informing patients to providing data ... More

Surveys of patients’ experiences are increasingly commonplace in healthcare. They are used to address a range of purposes, from driving quality improvements and informing patients to providing data for performance assessment of organisations. Making best use of such surveys requires an understanding of their design, sampling, administration, and analysis. This chapter addresses these issues, beginning with a brief discussion of the history of patient experience research. Patient experience surveys emerged as a reaction to patient satisfaction surveys. They are principally quantitative methods for collecting highly structured data, typically from relatively large numbers of people in order to provide statistically reliable results. They have been used in a wide range of settings (primary to tertiary care, many conditions etc) and for different purposes (eg QI, payment, international use, performance assessment, etc.). Surveys are extremely scalable: once a questionnaire and methodology exists they can easily be deployed to small or large numbers of people with only marginal cost increases. Thus they are a popular means of collecting locally representative data on a national basis. In general, though, surveys only tell us about what we have asked, and hence it is important to ensure that they are designed and used appropriately. Good, well designed surveys can be of considerable value for measuring and improving healthcare services: in this chapter we set out the key considerations around ensuring survey quality.Less

Scientific Survey Research: The Development of a Discipline

in The Total Survey Error Approach: A Guide to the New Science of Survey Research

The purpose of this book is to explain the survey research process in the context of this new approach to the field. The first three chapters establish the background by reviewing the development of ... More

The purpose of this book is to explain the survey research process in the context of this new approach to the field. The first three chapters establish the background by reviewing the development of the survey field, outlining and extending the total survey error approach, and providing a common understanding of the different survey modes. The middle of the book follows the total survey error approach's emphasis on the different sources of survey errors, discussing the different elements of surveys through a focus on the sources of error. The final chapters turn to broader and summary issues. The survey research field underwent scientization in the 1990s, applying theories from other fields to the survey research field. In particular, the cognitive revolution in psychology has led to new understanding of the survey response process and developments in statistics have provided new imputation techniques for dealing with missing data.Less