English title: The importance of items' level of measurement in investigating the structure and assessing the psychometric properties of multidimensional constructs

Author(s): Anastasia Charalampi -

Language: English

Type: Thesis / dissertation

Year: 2018

Abstract

Investigating the structure and assessing the psychometric properties of multidimensional scales before their application is a prerequisite of scaling theory. This involves splitting a sample of adequate size randomly into two halves and first performing Exploratory factor analysis (EFA) on one half-sample in order to assess the construct validity of the scale. Then the structure identified by EFA is validated by carrying out Confirmatory factor analysis (CFA) on the second half. As in any statistical analysis - whether univariate, bivariate or multivariate - the first and most important consideration is to ascertain the level of measurement of the input variables, in this instance the defining items of the scale. This guides the correct choice of the methods to be used. In this doctoral dissertation, we carry out the investigation and assessment of Schwartz’s human values scale included in the European Social Survey (ESS) when items are considered as pseudo-interval and the 2012 ESS measurement of wellbeing when items are considered as both ordinal and pseudo-interval. It is a methodological study aiming at demonstrating the importance of items’ level of measurement in carrying out a psychometric validation of multidimensional constructs. Schwartz’s human values scale has been widely used by social and cross-cultural psychologists in order to study differences in values among individuals and includes the ten motivationally distinct basic values which encompass the major value orientations recognized cross-culturally: power, achievement, hedonism, stimulation, self-direction, universalism, benevolence, tradition, conformity and security. The measurement of wellbeing provides an important indicator of the welfare of nations and presents opportunities for policy making. Researchers generally share the view of wellbeing as a multidimensional concept. The 2012 ESS measurement of personal and social wellbeing, a combination of theoretical models and evidence from statistical analysis, is defined as a six-dimensional construct: evaluative wellbeing, emotional wellbeing, functioning, vitality, community wellbeing and supportive relationships. The theoretical structure of both scales has been thoroughly documented. The analysis was based on the ESS Round 1 to Round 7 Data (2002-2014) for 16 European countries: Belgium, Denmark, Finland, France, Germany, Hungary, Ireland, Netherlands, Norway, Poland, Portugal, Slovenia, Spain, Sweden, Switzerland and the UK. In the case of Schwartz’s human values scale, EFA resulted in a two-factor solution for 41 cases, a three-factor solution for 51 cases and a four-factor solution for 20 cases. In the case of wellbeing scale, EFA resulted in a four-factor solution and a five-factor solution for seven countries, respectively, and a six-factor solution for two countries. These results were supported by CFA performed on the second half-samples. Subscales were constructed based on analysis of the total samples, and reliabilities, convergent and discriminant validities and internal consistencies were investigated. Although the definition of each subscale differs from the documented theoretical structures and across countries the analysis contributes to the growing research on the measurement of Schwartz’s human values and wellbeing by providing reliable and valid subscales for each country that can be used by social researchers in their analyses. The methodology presented may be easily applied to other Likert-type scales or scales using both ordinal and pseudo-interval items which are defined as multidimensional by theory. In the case of theory development, the preliminary considerations and the sequence of decisions for performing EFA may be applied with the appropriate modifications.

Type/degree:

Awarding institution: Panteion University of Social and Political Sciences

Number of pages: 898