Although agree–disagree (AD) rating scales suffer from acquiescence response bias, entail enhanced cognitive burden, and yield data of lower quality, these remain popular with researchers due to practical considerations (e.g., ease item preparation, speed administration, reduced administration costs). This article shows that if want use AD scales, they should offer 5 answer categories rather than 7 or 11, because the latter quality. is shown using four multitrait-multimethod experiments...

Although Agree/Disagree (A/D) rating scales are hugely popular in the social sciences, a large body of research conducted during more than five decades has documented bias that results from acquiescence responses to these items. This may be reason prefer questions with Item Specific (IS) response options, but remarkably little explored whether A/D scale indeed lower quality IS options. Using design combines advantages random assignment between-subjects experiment and multitrait-multimethod...

This paper aims to discover ‘How long can/should a survey be?’ by asking the question respondents themselves in web implemented Netquest fieldwork company Mexico 2016. It is that frequently asked, even if research has already been carried out on impact of length non-response or data quality. The study conducted for this concluded ideal median 10 minutes and maximum 20 minutes. reported lengths were significantly linked fact liked answering they trusted their are treated an anonymous way, but...

Individual behavior, particularly choices about prevention, plays a key role in infection transmission of vector-borne diseases (VBDs). Since the actual risk is often uncertain, individual behavior influenced by perceived risk. A low perception likely to diminish use preventive measures (behavior). If good indicator risk, then it has important implications context disease elimination. However, more research needed improve our understanding human transmission. The objective this study explore...

Evaluating the quality of data is a key preoccupation for researchers to be confident in their results. When web surveys are used, it seems even more crucial since have less control on collection process. However, they also possibility collect some paradata that may help evaluating quality. Using this paradata, was noticed respondents panels spending much time than expected complete surveys. This creates worries about obtained. Nevertheless, not known link between response times (RTs) and...

Surveys have been used as main tool of data collection in many areas research and for years. However, the environment is changing increasingly quickly, creating new challenges opportunities. This article argues that, this context, human memory limitations lead to inaccurate results when using surveys order study objective online behavior: People cannot recall everything they did. It therefore investigates possibility using, addition survey data, passive from a tracking application (called...

Abstract Purpose Despite the quick spread of use mobile devices in survey participation, there is still little knowledge about potentialities and challenges that arise from this increase. The purpose paper to study how respondents' preferences drive their choice a certain device when participating surveys. Furthermore, evaluates tolerance participants specifically asked carry out other specific tasks, such as taking photographs. Design/methodology/approach Data were collected by surveys...

Up until now, most surveys have used face-to-face interviews, postal mail, or the telephone to collect data. However, today difficulties of carrying out at reasonable costs increased. Simultaneously, new opportunities appeared. In particular, web surveys, which are usually cheaper, offer more flexibility, and can reach a large population in short time, becoming very attractive. Nevertheless, different modes data collection may lead coverage, sampling, nonresponse, measurement errors. We...

People’s willingness to share data with researchers is the fundamental raw material for most social science research. So far, survey have mainly asked respondents in form of answers questions but there a growing interest using alternative sources data. Less known about people’s these other kinds In this study, we aim to: 1) provide information people different types data; 2) explore reasons their acceptance or refusal, and 3) try determine which variables affect perform additional tasks. We...

In recent years, the number of surveys, especially online has increased dramatically. Due to absence interviewers in this survey mode (who can motivate respondents continue answering), some researchers and practitioners argue that surveys should not be longer than 20 min. However, so far, there been little research investigating how long think or could be. study, we therefore asked two panels Germany (one probability-based panel one nonprobability panel) about their opinions on ideal maximum...

Metered data, also called web-tracking are generally collected from a sample of participants who willingly install or configure, onto their devices, technologies that track digital traces left when people go online (e.g., URLs visited). Since metered data allow for the observation behaviours unobtrusively, it has been proposed as useful tool to understand what do and impacts this might have on offline phenomena. It is crucial, nevertheless, its limitations. Although some research explored...

So far, most surveys used face-to-face or telephone questionnaires in order to collect data. But the costs of achieving a survey using these traditional modes increase. At same time, response rates decrease, making idea switching mode very attractive. Because each has its own weaknesses and strengths, mixing data collection is becoming more popular. Nevertheless, combining different may be problematic if people answer differently depending on mode. Also, switch from unimode mixed-mode design...

We implemented an experiment within a smartphone web survey to explore the feasibility of using voice input (VI) options. Based on device used, participants were randomly assigned treatment or control group. Respondents in iPhone operating system (iOS) group asked use dictation button, which was translated automatically into text by device. with Android devices VI button recorded and transmitted audio file. Both groups answer open-ended questions standard entry. found that still presents...

Most mobile devices nowadays have a camera. Besides, posting and sharing images been found as one of the most frequent engaging Internet activities. However, to our knowledge, no research has explored feasibility asking respondents online surveys upload answer survey questions. The main goal this article is investigate viability an opt-in panel during web survey: First, photo taken in moment, second, image already saved on their smartphone. In addition, we want test what extent Google Vision...

Saris, Satorra, and Coenders (2004) proposed a new approach to estimate the quality of survey questions, combining advantages 2 existing approaches: multitrait–multimethod (MTMM) split-ballot (SB) ones. Implemented in practice, this led frequent problems nonconvergence improper solutions. This article uses Monte Carlo simulations understand why SB-MTMM is working well some cases but not others. The number SB groups crucial element: 3-group design performing better. However, 2-group can also...

The Internet is considered an attractive option for survey data collection. However, some people do not have access to it. One way address this coverage problem general population surveys draw a probabilistic sample and provide the selected units who it accept participate. This what knowledge panel Longitudinal Studies Social sciences (LISS) do. selection effect still possible. Units without previous might refuse participate in web panel, even if provided with necessary equipment. Thus,...

AbstractSince the idea of method variance was inspired by D. T. Campbell and Fiske in 1959, many papers have demonstrated an ongoing debate about both its nature impact. Often, entails upward bias correlations among observed variables—common bias. This article reports a split-ballot multitrait–multimethod experimental design for estimating 2 opposite biases: biasing from reaction to length response scale position survey items questionnaire downward effect poor data quality. The are derived...

Little is known about the reliability and validity in web surveys, although this crucial information to evaluate how accurate results might be and/or correct for measurement errors. In particular, there are few studies based on probability-based samples looking at web-specific response scales considering impact of having smartphone respondents. article, we start filling these gaps by estimating quality sliders compared radio button controlling device respondents used. We conducted therefore...

More and more respondents use mobile devices to complete web surveys. These have different characteristics, if compared PCs (e.g. smaller screen sizes higher portability). characteristics can affect the survey responses, mostly when a questionnaire includes sensitive questions. This topic was already studied by Mavletova Couper (2013), through two-wave experiment comparing results for same in Russian opt-in panel. We replicated this cross-over design, focusing on an panel Spain, involving...

Abstract Time and cost pressures, the availability of alternative sources data, societal changes are leading to a move from traditional face-to-face surveys web or mixed-mode data collection. While we know that there mode differences between (presence an interviewer not, type stimuli, etc.), it is not clear what extent these could threaten comparability collected in surveys. In this article, investigate measurement quality European Social Survey (ESS) Round 8 CROss-National Online (CRONOS)...

The formulation of theories and hypotheses is done at the level concepts. These concepts are often tested by operationalizing them using survey questions. However, measurement errors make it impossible for questions to measure interest perfectly. In order correct errors, information needed about their size, or size complement, quality. For USA Europe, a lot already known quality questions, but this has not yet been studied in some other parts world. paper, we use multitrait-multimethod...