Search results

The authors consider how the mode of data collection (Internet vs. paper) alters individuals’ responses to different types of survey questions, including subjective, recall, and factual questions. The authors isolate the measurement effect of the mode from the sample selection effect by exploiting predata in a convenience consumer panel. The authors propose using panelists’ reward point balance as exclusion restriction to correct for differing response probabilities by mode, because the reward point balance depends on the timing of the survey invitations and is a source of random variation in response incentive. The authors evaluate average and quantile measurement effects in a mixed-mode Web/paper survey and find statistically significant evidence of mode effects in subjective and recall questions.

The purpose of this paper is to examine the practice potential of self-administered drop-off as a survey mode for contingent valuation (CV) studies.

This paper conducts an empirical comparison of mode effects of two survey methods for improved ecological services in Beijing. Data were collected from a CV survey, which has two subsamples, one using face-to-face interviews and the other employing self-administered drop-off surveys.

There is some evidence of social desirability bias in the face-to-face interviews for the participation question; however, such effects do not carry over to subjects’ responses to the contribution decision. No difference is observed in sample demographics between modes. And satisficing effect is not observed in the drop-off survey in this study.

More well-controlled mode comparisons are warranted to test the robustness of the results; and collection time effects as well as the use of drop-off surveys for environmental valuation with different levels of complexity and familiarity are worthy of further study.

The authors find more similarities between drop-off and face-to-face surveys than differences therefore support the practice of self-administered drop-off surveys in CVM for environmental valuation.

This paper adds to the limited number of well-controlled mode comparisons in the CV surveys, and contributes to a better understanding of self-administered drop-off surveys, a potential low-cost alternative to face-to-face interviews in future CV applications.

Low response rates in web surveys and the use of different devices in entering web survey responses are the two main challenges to response quality of web surveys. The purpose of this study is to compare the effects of using interviewers to recruit participants in computer-assisted self-administered interviews (CASI) vs computer-assisted personal interviews (CAPI) and smartphones vs computers on participation rate and web survey response quality.

Two field experiments using two similar media use studies on US college students were conducted to compare response quality in different survey modes and response devices.

Response quality of computer entry was better than smartphone entry in both studies for open-ended and closed-ended question formats. Device effect was only significant on overall completion rate when interviewers were present.

Survey researchers are given guidance how to conduct online surveys using different devices and choice of question format to maximize survey response quality. The benefits and limitations of using an interviewer to recruit participants and smartphones as web survey response devices are discussed.

It shows how computer-assisted self-interviews and smartphones can improve response quality and participation for underprivileged groups.

This is the first study to compare response quality in different question formats between CASI, e-mailed delivered online surveys and CAPI. It demonstrates the importance of human factor in creating sense of obligation to improve response quality.

We examine sample characteristics and elicited survey measures of two studies, the Health and Retirement Study (HRS), where interviews are done either in person or by phone, and the Understanding America Study (UAS), where surveys are completed online and a replica of the HRS core questionnaire is administered. By considering variables in various domains, our investigation provides a comprehensive assessment of how Internet data collection compares to more traditional interview modes. We document clear demographic differences between the UAS and HRS samples in terms of age and education. Yet, sample weights correct for these discrepancies and allow one to satisfactorily match population benchmarks as far as key socio- demographic variables are concerned. Comparison of a variety of survey outcomes with population targets shows a strikingly good fit for both the HRS and the UAS. Outcome distributions in the HRS are only marginally closer to population targets than outcome distributions in the UAS. These patterns arise regardless of which variables are used to construct post-stratification weights in the UAS, confirming the robustness of these results. We find little evidence of mode effects when comparing the subjective measures of self-reported health and life satisfaction across interview modes. Specifically, we do not observe very clear primacy or recency effects for either health or life satisfaction. We do observe a significant social desirability effect, driven by the presence of an interviewer, as far as life satisfaction is concerned. By and large, our results suggest that Internet surveys can match high-quality traditional surveys.

Purpose — The paper is analysing the effect of adding a web survey to a traditional telephone-based national travel survey by asking the respondents to check in on the web and answer the questions there (Computer Assisted Web Interview, CAWI). If they are not participating by web they are as usual called by telephone (Computer Assisted Telephone Interview, CATI).

Design/methodology/approach — Multivariate regression analyses are used to analyse the difference in response rates by the two media and to analyse if respondents' answering by the two media have different travel patterns.

Findings — The analyses show that web interviews are saving money, even though a more intensive post-processing is necessary. The analyses seem to show that the CAWI is resulting in a more careful answering which results in more trips reported. A CAWI is increasing the participation of children in the survey and of highly educated. And it is offering a higher flexibility to answer after a couple of days off. The CATI is on the other hand more useful for the elderly. In addition, the CATI survey proved to be more useful for busy people and people not willing to participate in a survey at all. Young people and people with low resources who are difficult to reach by telephone are neither met on the web. Most of the differences in the response shares can be compensated by a weighting procedure. However, not all seems to be possible to compensate for. An effort to increase the number participating in the CAWI survey might increase the quality of the survey in general.

Originality/value of paper — In many countries authorities are considering how to reduce the cost of their national travel surveys. The value of the paper is to show that a combination of a CAWI and a CATI could be a good solution. Furthermore, it shows that the mixed mode could improve a CATI and therefore be the reason in itself to change methodology.

This paper reviews the current literature on theoretical and methodological issues in discrete choice experiments, which have been widely used in non-market value analysis, such as elicitation of residents' attitudes toward recreation or biodiversity conservation of forests.

We review the literature, and attribute the possible biases in choice experiments to theoretical and empirical aspects. Particularly, we introduce regret minimization as an alternative to random utility theory and sheds light on incentive compatibility, status quo, attributes non-attendance, cognitive load, experimental design, survey methods, estimation strategies and other issues.

The practitioners should pay attention to many issues when carrying out choice experiments in order to avoid possible biases. Many alternatives in theoretical foundations, experimental designs, estimation strategies and even explanations should be taken into account in practice in order to obtain robust results.

The paper summarizes the recent developments in methodological and empirical issues of choice experiments and points out the pitfalls and future directions both theoretically and empirically.

Purpose – This chapter provides a roadmap for future research and evaluation on violent extremist risk analysis.

Methodology/Approach – The authors synthesize the lessons learned from process evaluations of general violence risk assessment, bias research, survey designs, linguistic analyses, and spatial analyses, and apply them to the problem of violent extremist risk assessment and management.

Findings – The next generation of violent extremist risk assessment research will necessitate a focus upon process, barriers to effective implementation and taking the human element of decision-making into account. Furthermore, the development of putative risk factors for violent extremist attitudes and behaviors necessitates a movement toward more survey-based research designs. Future risk assessment processes may additionally take language and spatial components into account for a more holistic understanding.

Originality/Value – Based on existing literature, there is a paucity of research conducting process evaluations, survey designs, linguistic analyses, and spatial analyses in this area. The authors provide several roadmaps, assessments of respective strengths and weaknesses, and highlight some initial promising results.

In order to maximize response rates, a survey of Alaskan village public safety officers was conducted using both group‐administration methods (n=32) and mail‐administration methods (n=29). Included in the survey were questions related to officer job satisfaction and stress. It was expected that officers who completed the group‐administered survey would be more satisfied with their jobs and report less stress. Non‐parametric analysis of variance techniques were used to compare the responses for each of the administration methods. No statistically significant differences between the responses of the two groups of officers were found.