Suchergebnisse

Multidimensional scaling (MDS) is often used for the analysis of correlation matrices of items generated by a facet theory design. The emphasis of the analysis is on regional hypotheses on the location of the items in the MDS solution. An important regional hypothesis is the axial constraint where the items from different levels of a facet are assumed to be located in different parallel slices. The simplest approach is to do an MDS and draw the parallel lines separating the slices as good as possible by hand. Alternatively, Borg and Shye (1995) propose to automate the second step. Borg and Groenen (1997, 2005) proposed a simultaneous approach for ordered facets when the number of MDS dimensions equals the number of facets. In this paper, we propose a new algorithm that estimates an MDS solution subject to axial constraints without the restriction that the number of facets equals the number of dimensions. The algorithm is based on constrained iterative majorization of De Leeuw and Heiser (1980) with special constraints. This algorithm is applied to Levi's (1983) data on political protests.

Values are central to public debates today. Human values convey broad goals that serve as guiding principles in a person's life and value priorities differ across people in society. Groups in society holding opposing values (e.g., universalism versus security) will make different choices when voting in an election. Whereas over time, values are relatively stable, the number and type of political parties as well as the political values they communicate and disseminate have been changing. Groups of people holding the same human values may therefore vote for another (new) party in a later election. We focus on analyzing the relationship between human values and voting in elections, introducing a new methodology to analyze how value profiles relate to political support over time. We investigate the Dutch multi-party political system over five waves of the European Social Survey, spanning 2002 until 2010. Whilst previous research has focused on individual values separately and focused on voters only, we (1) distinguish groups holding a similar set of opposing and compatible values (value profile) instead of focusing on single values in the the entire population; (2) incorporate a correction for differences in scale use in our model; (3) compare voting over time; (4) include non-voters, a growing group in Dutch society. We find evidence that specific value profiles are related to voting for a specific set of political parties. We also find that specific value profiles distinguish non-voters from voters and that voters for populist parties resemble non-voters.

Abstract Human values drive dierent kinds of abstract behaviour, while established value scales are pervasive in survey research. We focus on analyzing the relationship between human values and voting in elections, introducing a new methodology to analyze how value profiles relate to political support over time. To illustrate our procedure, we investigate the Dutch multi-party political system. Values measured using rating scales over five waves of the European Social Survey, spanning 2002 until 2010, are analysed. Whilst previous research have focused on values separately, we (1) relate all political parties participating in the election to human values using a segmentation approach in which value profiles are used instead of individual values; (2) compare voting over time; (3) include non-voters; and (4) adjust for individual dierences in response style. The adjustment for response styles allow us to uncover valid insights into the relationship between values and voting. We find evidence that specific value profiles are related to voting for certain political parties and that non-voters can also be distinguished by unique value profiles.