A factor analytic comparison of dichotomous and polytomous response categories
- Authors: Vorster, Paul Petrus
- Date: 2012-06-06
- Subjects: Psychometrics , Psychiatric rating scales , Factor analysis , Factorial experiment designs
- Type: Mini-Dissertation
- Identifier: uj:2487 , http://hdl.handle.net/10210/4941
- Description: M.Comm. , It was investigated whether dichotomous (2-point) or polytomous (5-point) rating scales have superior functioning on the personality construct Soft-Heartedness for the South African Personality Inventory (SAPI). The optimal number of rating scale categories for a personality measure was explored. The participants comprised students of diverse racial and cultural backgrounds at a South African tertiary institution (N =708). Two alternate forms of a test measuring Soft-Heartedness were administered to two alternated groups (n1 = 344; n2 = 364). Either version of the test contained a 2-point and 5-point version. These two formats were then factor analysed and subjected to a tetrachoric/polychoric correlation analysis. They were also tested for reliability using the Cronbach Alpha coefficient and composite reliability coefficient. In addition, the coefficient of congruence was established. It was found that the 2-point scale has more functional psychometric properties than the 5-point scale regarding the factor structure and composite reliability. This was attributed to cultural, perceptual, linguistic, educational, and test-experience components.
- Full Text:
Determinants of logistics outsourcing performance among small and medium enterprises
- Authors: Mageto, Joash , Prinsloo, Gerrie , Luke, Rose
- Date: 2020
- Subjects: Logistics outsourcing performance , SMEs , Factor analysis
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/428385 , uj:36840 , Citation: Mageto, J., Prinsloo, G. & Luke, R. 2020. Determinants of logistics outsourcing performance among small and medium enterprises.
- Description: Abstract: The purpose of this study is to establish determinants of logistics outsourcing performance and their relationship with logistics performance among manufacturing small and medium enterprises (SMEs). The increasing use and challenge of logistics outsourcing require that SMEs establish relationship factors that determine high outsourcing performance to enhance overall logistics performance. Data was collected from 406 SMEs using a structured questionnaire. Factor analysis was applied and four constructs were extracted; three were found to be determinants. Partial least squares structural equation modelling was performed to determine the associations among the constructs. Communication-trust, innovation and cooperation between the manufacturing SMEs and logistics service providers were identified as key determinants of logistics outsourcing performance. Strong associations were validated between communication-trust, innovation and cooperation. Only communication-trust was positively associated with logistics performance. The results guide SME managers to promote communication-trust in logistics outsourcing relationships.
- Full Text:
Investigating the quality of university education : a focus on supply chain management
- Authors: Mageto, Joash , Luke, Rose , Heyns, Gert
- Date: 2020
- Subjects: Service quality , Supply chain education , Factor analysis
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/452737 , uj:39941 , Citation: Mageto, J., Luke, R. & Heyns, G. 2020. Investigating the quality of university education : a focus on supply chain management.
- Description: Abstract: While the quality of higher education has received attention from researchers globally, its focus has been mainly on universities in ‘developed country’ contexts. There has been limited research on the quality of higher education in African universities, and even less that has focused on the discipline of supply chain management. In this paper, the quality of supply chain education of five universities in Kenya is investigated using a SERVPERF model. Data were collected through a structured questionnaire administered to 781 students enrolled for a supply chain management qualification. The data were analysed through confirmatory factor analysis and one-way analysis of variance. The findings are fourfold: (1) the service quality of supply chain education is at medium level in terms of the SERVPERF metrics; (2) four dimensions were identified by students as the most important aspects of service quality: course-centeredness, academic and support staff helpfulness, service excellence and learning facilities; (3) a four-factor SERVPERF model of supply chain service quality is developed and (4) service quality was significantly different across the selected universities. Although the service quality was rated at a medium level overall, the variability in quality across universities should alert educators and management to the need for a coordinated effort to improve particular aspects of students’ learning experiences. The study contributes to the body of knowledge by establishing that SERVPERF is a four-factor model in the higher education sector.
- Full Text:
Problems with the factor analysis of items: solutions based on item response theory and item parcelling.
- Authors: De Bruin, G.P.
- Date: 2004
- Subjects: Factor analysis , Unidimensional scales , Non-linear relations , Rasch rating scale model , Locus of control inventory
- Type: Article
- Identifier: uj:6570 , http://hdl.handle.net/10210/2870
- Description: The factor analysis of items often produces spurious results in the sense that unidimensional scales appear multi-dimensional. This may be ascribed to failure in meeting the assumptions of linearity and normality on which factor analysis is based. Item response theory is explicitly designed for the modelling of the non-linear relations between ordinal variables and provides a strong alternative to the factor analysis of items. Items may also be combined in parcels that are more likely to satisfy the assumptions of factor analysis than do the items. The use of the Rasch rating scale model and the factor analysis of parcels is illustrated with data obtained with the Locus of Control Inventory. The results of these analyses are compared with the results obtained through the factor analysis of items. It is shown that the Rasch rating scale model and the factoring of parcels produce superior results to the factor analysis of items. Recommendations for the analysis of scales are made.
- Full Text:
Structural equation modelling the leaching of oxidised copper-cobalt ore in HCl aqueous solution
- Authors: Kime, Méschac-Bill , Mulaba-Bafubiandi, Antoine
- Subjects: Leaching optimisation , Oxidised copper-cobalt ore , Structural Equation Modelling (SEM) , Multiple regression , Path analysis , Factor analysis , SPSS statistics
- Language: English
- Identifier: http://hdl.handle.net/10210/18571 , uj:16015 , Citation: Kime, M-B., Maluba-Bafubiandi, A. Structural equation modelling the leaching of oxidised copper-cobalt ore in HCl aqueous solution.
- Description: Abstract: Structural Equation Modelling (SEM) is now widely used to explore the joint performance of factors affecting a process and to quantify the effect of each factor in the presence of the others. In this research work, SEM analysis was conducted to develop Structural Equation Models that well predict the leaching behaviour of Cu, Co, Ni and Fe in HCl aqueous solution of an oxidised copper-cobalt ore. A comprehensive set of experimental batch leaching tests was executed to study the effect of operating variables (pH, time, temperature and stirring speed) on the relative leaching yields of Cu, Co, Ni and Fe during the leaching of an oxidised copper-cobalt ore sample in an HCl aqueous solution. The gangue acid consumption was also measured to aid in understanding the behaviour of the gangue. The experimental results obtained were statistically analysed and modelled using the SEM procedure. The Structural Equation Models obtained showed that Cu and Co leaching yields had a strong positive dependence on both the leaching time and leaching temperature, while Fe leaching yield had a moderate dependence on the leaching temperature, stirring speed and the covariate Z (Z = stirring_speed*pH). On the contrary, Ni leaching yield had a strong negative dependence on both the stirring speed and the covariate Z. The Structural Equation Models agreed fairly with the experimental results obtained upon leaching. This is a clear indication that the models can be used to predict the leaching yields given a set of leaching parameters.
- Full Text:
The dimensionality of the general work stress scale: a hierarchical exploratory factor analysis.
- Authors: De Bruin, G.P.
- Date: 2006
- Subjects: General work stress , Factor analysis , Work stress scale
- Type: Article
- Identifier: uj:6564 , http://hdl.handle.net/10210/2864
- Description: This study examined the dimensionality or factor structure of the General Work Stress Scale (GWSS), which is a brief measure of subjectively experienced or felt work stress. The responses of two independent groups of adult workers were subjected to maximum likelihood factor analysis. In both groups a three factor solution provided the best fit with the data. A higher order factor analysis with an orthogonal Schmid-Leiman transformation showed that in both groups, responses to the items are dominated by a general factor, which might be labelled General Work Stress. Three minor group factors were identified: a motivational factor reflected by a desire to leave the organisation, an affective factor reflected by a tendency to worry, and a cognitive factor reflected by concentration and attentional difficulties. Overall, the results provide support for the construct validity of the GWSS as a measure of subjectively experienced work stress.
- Full Text:
The factor structure of the Edinburgh postnatal depression scale in a South African peri-urban settlement.
- Authors: De Bruin, G.P. , Swartz, L. , Tomlinson, M. , Cooper, P. , Molteno, C.
- Date: 2004
- Subjects: Edinburgh postnatal depression scale , EPDS , Factor analysis
- Type: Article
- Identifier: uj:6571 , http://hdl.handle.net/10210/2871
- Description: The factor structure of the Edinburgh Postnatal Depression scale (EPDS) and similar instruments have received little attention in the literature. The researchers set out to investigate the construct validity and reliability of the EPDS amongst impoverished South African women. The EPDS was translated into isiXhosa (using Brislin’s back translation method)and administered by trained interviewers to 147 women in Khayelitsha, South Africa. Responses were subjected to maximum likelihood confirmatory factor analysis. A single factor structure was found, consistent with the theory on which the EPDS was based. Internal consistency was satisfactory (a = 0.89).
- Full Text: