Suchergebnisse

Michael Bergmann: Panel Conditioning: Wirkungsmechanismen und Konsequenzen wiederholter Befragungen. Baden-Baden: Nomos 2015. 9783848720163

Fixed-effects-Modelle sind zu einem wichtigen Werkzeug der Kausalanalyse geworden, da sie die Kontrolle von unbeobachteter Heterogenität ermöglichen. Bis heute wurden fixed-effects-Modelle für kontinuierliche und dichotome abhängige Variablen entwickelt und für viele Statistikpakete implementiert. Für multinominale abhängige Variable wurde von Chamberlain (1980) ein solches Modell entwickelt, es liegt aber keine allgemein anwendbare Umsetzung vor. Die vorliegende Arbeit schließt diese Forschungslücke mit der ersten Umsetzung des Modells von Chamberlain in einem weitverbreiteten Statistikpaket (Stata). Die Anwendbarkeit wird durch Erweiterungen der Arbeiten von Schröder (2010) im Bereich der Familiensoziologie und Kohler (2005) im Bereich der politischen Soziologie gezeigt. ; Fixed effects models have become a prime tool for causal analysis, as they allow to control for unobserved heterogeneity. As of today, fixed effects models have been derived and implemented for many statistical software packages for continuous, dichotomous and count-data dependent variables. For multinomial categorical dependent variables such a model has been derived in a seminal paper by Chamberlain (1980), but no implementation is available. The dissertation on hand closes this research gap by delivering the first implementation of Chamberlain's model in a widely available statistical package (Stata). Its applicability is shown by extending Schröder's (2010) work in the sociology of the family and Kohler's (2005) work in political sociology.

This data brief describes the European Union Statistics on Income and Living Conditions (EU-SILC). Detailed data on income and taxes are collected, as well as information on material deprivation, labour, housing, childcare, health, access to and use of services, and education. Although primarily a social policy instrument that addresses the information needs of policymakers and is used for social monitoring at the European level, EU-SILC is also closely geared to the needs of researchers and provides an excellent database for evidence-based research on a wide variety of aspects of income, income poverty, material poverty, health, and well-being in Europe. EU-SILC is composed of national probability sample surveys and is conducted annually. The target population comprises private households. Observation units are households and all current household members. EU-SILC provides cross-sectional and longitudinal data. The data are composed of a fixed core module, and annually changing ad-hoc modules. Launched in 2003 and revised with effect from 2021, EU-SILC is currently implemented in all EU Member States and in 11 non-EU countries. During the revision process, many suggestions from the research community were incorporated.

Almost all comparative research on the effects of employment protection legislation of regular employees (EPLR) is based on the index of the OECD. This study argues that this index is methodologically flawed and proposes a new EPLR index, following a theory-driven formative index construction approach. To demonstrate the implications using the OECD EPLR index versus the new index, we use two empirical applications: First, the effects of EPLR on perceived job insecurity, using multi-level models with data from the European Social Survey, the European Working Condition Survey, and the European Quality of Life Survey. Secondly the temporary employment risk for new hires, using multi-level models with data from the European Labour Force Survey. Whereas the results based on the OECD EPLR index significantly deviate from the hypotheses in the literature, the results using the new EPLR index is compliant with the hypotheses in the literature. This demonstrates higher criterion validity of the theory-driven new EPLR index and also calls for replications of previous research that is based on the index of the OECD.

Abstract
This paper adds to the discussion on the value of online surveys for political science research. Mainly because of the lower costs, collecting survey data over the web has become increasingly popular in recent years, despite the higher sampling and coverage error in web-only surveys, especially online access polls. Recruiting respondents for the actual panel surveys based on a representative sample using a different mode is regarded as a solution to the sampling problem. Two approaches have been used to tackle the problem of coverage error: Providing respondents with computers (e.g. LISS, ELIPPS, GIP) and offering a different mode than online to respondents, thereby adopting a mixed mode design (e.g. paper as in GALLUP, GESIS Panel). The literature suggests that offering participation in the respondent's preferred mode affects response rates positively but not much is known about respondents' reasoning to choose a specific mode. We argue that it is important to understand this decision to evaluate the selection into online surveys and the consequences this has for data quality. We investigate this question by drawing on data from the GESIS Panel face-to-face recruitment interview for building a mixed mode access panel (paper and web) in Germany that gave a mode choice to internet users. Our results suggest that web literacy, age and education alone do not explain the mode choice but that affinity towards the technology related to the online mode has an independent effect. In a second step, we analyse the effect of this selection mechanism on answers to questions on typical variables used in political participation research such as media competence, political interest and civic duty in the subsequent mixed mode survey. We assess the added value of adopting a mixed-mode strategy. The results inform the evaluation of biases in unimode online surveys.

"Der Beitrag stellt den Forschungsstand zur Frage dar, inwieweit in westlichen Industrieländern ein kausaler Zusammenhang zwischen der Erwerbstätigkeit und der Fertilität von Frauen besteht und in welche Richtung die Kausalität verläuft. Vorliegende Makrostudien können die Frage nach dem kausalen Zusammenhang zwischen Erwerbstätigkeit und Fertilität aufgrund fehlender Drittvariablenkontrolle und der Möglichkeit eines ökologischen Fehlschlusses nicht klären. Längsschnittsanalysen auf der Mikroebene zeigen einen negativen Effekt von gegenwärtiger Erwerbstätigkeit auf die Übergangsrate zu einem (weiteren) Kind. Es besteht jedoch der Verdacht, dass es sich bei diesem Effekt nicht um einen Kausaleffekt handelt, sondern um einen Selbstselektionseffekt. Auf Grundlage von Längsschnittsstudien zum Einfluss der Fertilität auf die Erwerbstätigkeit kann hingegen geschlossen werden, dass die Fertilität einen kausalen Effekt auf die Erwerbstätigkeit hat. Problematisch bleibt allerdings - wiederum aufgrund möglicherweise vorliegender Selbstselektion - die genaue Quantifizierung dieses Effekts." (Autorenreferat)

This thematic issue examines the insurance function as a mechanism to underlie wealth effects on various outcomes. The articles in this issue shed an innovative light on the insurance function of wealth concerning a range of topics relevant to social stratification and social policy researchers. This editorial provides an overview of the contributions of this
thematic issue and highlights some gaps and remaining open questions. Altogether, the contributions suggest that wealth can provide insurance against adverse life events in various contexts. However, this insurance effect depends on welfare state characteristics, wealth portfolios, and the way families handle their wealth.

Wealth plays an important role in social stratification but the results that can be obtained when analyzing wealth as a predictor variable depend on modeling decisions. Although wealth consists of multiple components it is often operationalized as net worth. Moreover, wealth effects are likely non-linear, but the functional form is often unknown. To overcome these problems, we propose to 1) split up net worth into gross wealth and debt and evaluate their joint effect and 2) use non-parametric Generalized Additive Models. We show in a simulation study that this approach describes systematic wealth differences in more detail and overfits less to random variation in the data than standard approaches. We then apply the approach to re-analyze wealth gaps in educational attainment in the US. We find that the operationalization of wealth as net worth results in a misclassification of which children have the best and the worst educational prospects. Not negative net worth is associated with the worst educational prospects but only the combination of low gross wealth and low debt. The most advantaged group are not only children with high net worth but all children with high gross wealth independent of the households' amount of debt.

While debt is not problematic per se, it can become an additional burden when people experience negative life events–like unemployment, a severe disease, divorce, or their partner's death–which can be detrimental for individuals' subjective wellbeing. We investigate first, a potential moderating effect of economic resources or, better yet, lack thereof in the relations between negative life events and general life satisfaction, and second, whether this moderating effect is a function of state-level policies. We expect that, on average, debt has a reinforcing effect on the negative relationship between negative life events and general life satisfaction. Moreover, we expect that country-level policies protecting individuals from the negative consequences of experiencing a negative life event or indebtedness can explain the country differences in the moderating effect of debt. We test our assumptions among the population aged 50+ applying data from the Survey of Health, Ageing and Retirement (SHARE). We apply a two-stage fixed-effects regression approach to estimate the moderation effect of debt on the relationship between negative life events and general life satisfaction within and across countries. Although we find an almost zero average moderating effect of debt across countries, we find large variance in the moderating effects between countries. This variance can be explained by debt regime, but not by the generosity of the public unemployment and the public health systems, or the level of gender equality.

"Steadily declining response rates lead to an increased usage of incentives in all kind of surveys. As for mail surveys, much empirical evidence supporting the usage of unconditional incentives is available (Berk, Mathiowetz, Ward and White 1987; Church 1993). For face-to-face studies, however, fewer results are available, and even less often in experimental settings (Martin, Abreu and Winters 2001; Singer, Hoewyk, Gebler, Raghunathan and McGonagle 1999). The authors conducted a three wave panel CAPI survey (N=600), where respondents were randomly assigned to three experimental groups: the first group received an unconditional incentive in form of a 10 Euro voucher, the second group was promised a 10 Euro voucher conditional upon participation, the third group was a control group that received no incentive. The allocation to a given experimental group was constant across the three waves and interviewers were kept blind to the experimental conditions. This research adds to the methodological literature in several ways: firstly, the authors compared the effectiveness of prepaid and conditional monetary incentives in a face-to-face interview in cross-sectional and longitudinal perspective, and found that conditional incentives performed significantly better in retaining respondents till the third wave. Secondly, they controlled for accurateness of the interviewers' work on the field, and found evidence that improving selection and training of interviewers remains mandatory, since poor quality in the interviewer pool cannot be compensated by incentives." (author's abstract)