Suchergebnisse

"Landline surveys suffer from an increasing risk of excluding a relevant share of the population.
To analyze and correct telephone coverage issues, face-to-face surveys are often used, which contain questions about landline ownership and registration. Others use dual frame approaches and compare results from the landline with another mode. However, such surveys lack information about unobserved sample members. In this article we analyze representation bias using a household survey with a sample drawn from a population register, where landline is used for households with a matched landline, and face-to-face for those without. We distinguish between the different components of nonobservation, including landline undercoverage, non-contact, and non-cooperation, by either incorporating face-to-face sample members or not, and by the fieldwork phases to recruit households and individuals. Our main interest is how biases from each of these components add up to a final representation bias in the responding sample. In
addition, we analyze income and deprivation differences by either including face-to-face
sample members or not. The strongest representation bias in the telephone sample on the household level is caused by telephone undercoverage. The combined sample suffers much less from representation bias, which mostly stems from noncooperation. In terms of income and deprivation differences, our results show that the face-to-face sample is poorer than the telephone
sample and needs to be considered for unbiased estimates. Based on these findings we offer some fieldwork recommendations to help reduce selection bias based on the different reasons for nonobservation." (author's abstract)

"One of the key problems in conducting surveys is convincing people to participate. However, it is often difficult or impossible to determine why people refuse. Panel surveys provide information from previous waves that can offer valuable clues as to why people refuse to participate. If we are able to anticipate the reasons for refusal, then we may be able to take appropriate measures to encourage potential respondents to participate in the survey. For example, special training could be provided for interviewers on how to convince potential participants to participate. This study examines different influences, as determined from the previous wave, on refusal reasons that were given by the respondents in the subsequent wave of the telephone Swiss Household Panel. These influences include socio-demography, social inclusion, answer quality, and interviewer assessment of question understanding and of future participation. Generally, coefficients are similar across reasons, and between-respondents effects rather than within-respondents effects are significant. While 'No interest' reasons are easier to predict, the other reasons are more situational. Survey-specific issues are able to distinguish different reasons to some extent." (author's abstract)

"Little is known about sample behavior and fieldwork effects of different incentives introduced in a household panel survey. This is especially true for telephone surveys. In a randomized experiment, the Swiss Household Panel implemented one prepaid and two promised non-monetary incentives in the range of 10 to 15 Swiss Francs (7-10 EUR), plus a no incentive control group. The aim of the paper is to compare effects of these incentives especially on cooperation, but also on sample selection and fieldwork effort, separated by the household and the subsequent individual level. We find small positive cooperation effects of the prepaid incentive on both the household and the individual level especially in larger households. Sample composition is affected to a very minor extent. Finally, incentives tend to save fieldwork time and partially the number of contacts needed on the individual level." (author's abstract)

"Interviewer performance with respect to convincing sample members to participate in surveys is an important dimension of survey quality. However, unlike in CAPI surveys where each sample case 'belongs' to one interviewer, there are hardly any good measures of interview performance for centralised CATI surveys, where even single contacts are assigned to interviewers at random. If more than one interviewer works one sample case, it is not clear how to attribute success or failure to the interviewers involved. In this article, the author proposes two correlated methods to measure interviewer contact performance in centralised CATI surveys. Their modelling must take complex multilevel clustering effects, which need not be hierarchical, into account. Results are consistent with findings from CAPI data modelling, and the author finds that when comparing effects with a direct ('naive') measure of interviewer contact results, interviewer random e ffects are largely underestimated using the naive measure." (author's abstract)

'In diesem Artikel werden Ausmaß und Selektivität der Panelattrition im Schweizer Haushalt Panel zwischen den Wellen zwei (2000) und sieben (2005) untersucht. Die Stichprobenbasis bilden die Teilnehmer der ersten Welle (1999). Nach einem Vergleich der Höhe und der Selektivität der Attrition mit anderen Haushaltpanels wird die Selektivität in zwei Schritten modelliert: zunächst durch Übergangsmodelle, in denen jeweils zwei aufeinanderfolgende Wellen verwendet werden, und schließlich durch ein Längsschnittmodell unter Verwendung aller Wellen. Letzteres enthält Wellendummies. Die Übergangsmodelle dienen dazu, Selektivität zu identifizieren und weiterzuverfolgen, d.h. zu erkennen, ob sich eine initiale Selektivität im Laufe der Zeit verstärkt oder ausgleicht. Mit dem Längsschnittmodell können spezifische Effekte von Kovariaten in einzelnen Wellen untersucht werden, wobei die Basisattrition kontrolliert wird. Insbesondere können die Auswirkungen einzelner Panelereignisse analysiert werden. Die Ergebnisse bestätigen bisherige Erkenntnisse aus der Literatur: Personen, die aus dem Panel aussteigen sind tendenziell jünger und männlich, Ausländer, mit geringem sozialen und politischen Interesse und Engagement, die mit verschiedenen Lebensaspekten Unzufriedenen, die in Haushalten mit hohem Unit-Nonresponse lebenden und diejenigen mit schlechterer Befragungsqualität. Dieses Muster bleibt im Lauf des Panels bestehen. Die hohe Attrition in zwei Panelwellen, die vermutlich von singulären Ereignissen herrühren, ist nicht übermäßig selektiv.' (Autorenreferat)

Measuring change over time is one of the main purposes of longitudinal surveys. With an increase in the use of web as a mode of data collection it is important to assess whether the web mode differs from other modes with respect to the number of changes and events that are captured. We examine whether telephone and web data collection modes are compara­ble with respect to measuring changes over time or experiencing events. Using experimen­tal data from a two-wave pilot of the Swiss Household Panel, we investigate this question for several variables in the domain of work and family. We find differences for the work-related variables, with web respondents more likely to re­port changes. These differences do not disappear once the socio-demographic composition of the sample is taken into consideration. This suggests that these differences are not driven by observed different characteristics of the respondents who may have self-selected into one or the other mode. Contrary to work-related variables, a termination of a relationship was more common in the telephone group. This shows that one mode does not necessarily measure more change or events than another; it may depend on the variable in question. In addition, the difference in the protocol mattered: a web respondent in a household that participated fully by web sometimes differed from a web respondent in a household that had a household interview by phone. Nonetheless, the telephone group differed more from the various web protocols that the web protocols among themselves. With more household panel surveys introducing web questionnaires in combination with more traditional face-to-face and telephone interviews, this study adds to our understand­ing of the potential consequences of mixing modes with respect to longitudinal data analy­sis.

The majority of European, as well as many other, countries responded to the outbreak of the new coronavirus with a closure of schools and universities. The expectation of policy makers was that schools and universities would continue to provide lessons online and that students would engage in home learning. How much home learning has there been? We use nationally representative, longitudinal data on 14- to 25-year-old Swiss students to analyze the effects of school closures on studying time. Our results show that students reduced, on average, their studying time from 35 to 23 hours per week. This reduction was stronger for students in secondary school age than for students older than 18. Contrary to our expectations, these reductions in studying time did not vary between male and female students. In addition, children from families with highly educated parents reduced their studying time in absolute terms more than children from families with low educated parents. In relative terms, reductions in children's studying time did not vary by parental education. We also found some variation in the reduction in studying time across the three linguistic regions in Switzerland. Taken together, our findings show that studying time was considerably reduced during the closure of schools. We therefore conclude by suggesting political measures that can compensate for the loss in studying time a generation of Swiss students experienced between March and July 2020.

This paper is motivated by two recent articles which show that numerous studies which analyzed gender of interviewer effects did not take interviewer nonresponse selection effects into account. For example, interviewers may be more successful at recruiting respondents with characteristics similar to themselves and who give answers that are similar to their own, and this may result in spurious gender of interviewer effects. Our research is novel because it uses data from a large panel survey in which the same respondent is asked the same questions repeatedly by interviewers of random genders using the centralized telephone mode. We use the panel design to show the importance of checking for all relevant variables in models where selection may cause bias. To this end, we use respondent fixed effects models as a reference to yield unbiased coefficients. We find gender of interviewer effects that are in line with social desirability theory on gender issues such as female discrimination. However, not all gender-related questions are affected by gender of interviewer effects and, in addition, we do not find any effects on political and (factual) household task related questions. In line with the notion of social distance, there is a higher likelihood that answers respondents are less comfortable with are given to interviewers of the same gender regarding (sensitive) health questions.