This article outlines several techniques for analyzing panel data with a dichotomous dependent variable. This presentation is inspired by the classic work of Paul Allison [1999]. An example analysis is presented where public attitudes toward restitution of church property in the Czech Republic is explored using panel data. Here the focus is on exploring changes in the intra-personal agenda of respondents on this specific issue. There are three main conclusions from this research: (1) media exposure and (2) the education level of the respondent increase the odds of the church restitution issue being mentioned by a respondent as being important, and (3) mention of the church restitution issue in a particular wave of the panel survey is negatively associated with mention of this issue in later waves of the panel study examined. These findings are discussed in terms of their methodological and substantive implications., František Kalvas ... [et al.]., and Obsahuje bibliografii a bibliografické odkazy
The present paper deals with the Brno Social Study, a rather extraordinary questionnaire survey given its extent and time (1947). Data analysis was forestalled by the political transformation after 1948, but the questionnaires were preserved. We have inherited a unique set of data for a historical-sociological analysis focusing both on the population of industry workers and on the social structure of Czech society in the advent of the communist coup. The Brno Social Study is contextualized in the state of post-war sociology, and the avenues toward its inception and implementation are mapped. The central part of the paper analyses the survey data from a contemporary analytical perspective, discussing the dataset’s representativeness. The primary objective of the paper is to propose, and initiate scholarly debate about, a feasible methodology for analysing the archived data today. The methodology serves to construct a representative sample through a combination of purposive, quota and random sampling; to determine the respondents’ socio-economic status using both ISCO and an original conceptualization of working class status; and to present certain data on respondents’ lifestyles that might be of interest for future analyses., Dušan Janák, Martin Stanoev a Petr Hušek., and Obsahuje bibliografii
istorically speaking divorce is a relatively recent phenomenon. Divorce has become more important over the last century and has undoubtedly had an impact on the social reproduction strategies typically linked to marriage. In this paper use is made of the concept of Assortative Mating to explore if initial and subsequent marriage partner choices differ on the basis of heterogamy. This research question is formulated in terms of two contrasting hypotheses: (1) the learning and (2) the marriage market hypotheses (Gelissen 2004). These two perspectives form the basis of the theoretical framework used in the empirical analyses reported. Here logistic and linear regression and log-linear modelling techniques are used. The data used to test the learning and marriage market hypotheses contains information on all officially recorded marriages in the Czech Republic over a ten year period (1994-2004) gathered by the Czech Statistical Office. The results presented reveal that divorce changes the socially reproductive aspects of marriage choice strategies, and these changes vary systematically on the basis of gender. Whereas first and subsequent marriage choices are very similar for men, repeated marriage choices for women are on the whole more diverse. A number of explanations explaining this gender based difference are presented. These explanations centre on dissimilarities in the context of repeated choices for men and women., Petr Fučík., 5 grafů, 2 tabulky, Obsahuje bibliografii, and Anglické resumé
This article reports the results of a content analysis of recently published papers on the relationship(s) between socioeconomic status and health. This study explores how scholars conceptualize and measure socioeconomic status and health. Consequently, this research investigates if significant differences in measurement exist both across subfields within sociology and across disciplines. The evidence presented reveals a remarkable variation in measurement strategies. Moreover, this variation exhibits a pattern that is not entirely predictable. This article concludes by presenting in detail some of the most widely used health indicators and proposing that current measurement practice may be improved by utilizing some more advanced scaling strategies., Martin Kreidl, Lucie Hošková., 4 tabulky, Obsahuje bibliografii, and Anglické resumé
Advances in the statistical analysis of longitudinal data has been so rapid, that it has been difficult for empirically oriented social scientists to remain informed of all new developments in this important area of social methodology. This article offers some guidance on the use of various types of panel data analysis techniques, paying particular attention to the analysis of longitudinal panel data. The aim of this article is to describe in a succinct manner the logic underpinning a number of panel analysis techniques; outlining the types of inferences that can be drawn from employing specific techniques, and providing the reader with references to the literature associated with particular forms of panel data analysis. Five types of panel data analysis are discussed: Event history analysis, Sequential analysis, Hierarchical linear (or multi-level) modeling (with application to longitudinal data analysis), Structural equation modeling with longitudinal data, and use of Log- linear and Markov chain models for longitudinal data with categorical variables., Petr Pakosta, Petr Fučík., and Obsahuje bibliografii a bibliografické odkazy