This study is part of the quantitative work within the SAPI project and builds on the SAPI literature, resulting in a more acceptable instrument. This was investigated by comparing the results obtained by administering both block and random versions of the SAPI to a total sample of N=429 respondents in several private nursing institutions. This strategy involved conducting an exploratory factor analysis on each of the nine factors for both random and block response sets.
Using the strategy, the block response set was found to provide a better structurally and factorially valid framework when applied to the conceptual personality structure of the SAPI. To the SAPI Project Team for providing me with the financial assistance of the SANPAD SAPI Scholarship (Ref. 9/42) to carry out and complete my studies and for the opportunity to contribute to the project.
- INTRODUCTION TO THE STUDY
- BACKGROUND
- PROBLEM STATEMENT
- PURPOSE STATEMENT
- RESEARCH OBJECTIVES
- ACADEMIC VALUE AND CONTRIBUTION OF THE STUDY
- DELIMITATIONS AND ASSUMPTIONS
- DELIMITATIONS
- ASSUMPTIONS
- DEFINITION OF KEY TERMS
- RESEARCH METHODOLOGY
- CHAPTER LAYOUT
- CHAPTER SUMMARY
The data were analyzed using an exploratory factor analysis to establish the factorial validity of the SAPI. To accumulate evidence, the purpose of the study was to determine whether block or random-item order generates the best factorial construct fit within the framework of the SAPI. The purpose of this study was to validate the factorial structure of the SAPI by comparing the results of random- and block-item ordering within the SAPI.
Valchev (2012) identified this as a limitation in current knowledge of South African personalities and suggested that an investigation into the item order of the SAPI was necessary. Therefore, this study aimed to provide new knowledge in terms of the development of the SAPI within the South African context.
LITERATURE REVIEW
- INTRODUCTION
- THE DOMAIN OF PERSONALITY
- Introduction
- Definition of Personality
- Origin of the study of Personality
- Evolution of the study of Personality
- Taxonomies of Personality
- ASSESSMENT OF PERSONALITY
- Introduction
- Use of Testing for Personality
- Origin of Psychological Testing
- Creating Taxonomies for Personality Testing
- CROSS-CULTURAL PERSONALITY ASSESSMENT
- Introduction
- Concerns for imported assessments based on the Five Factor Taxonomy
- Cross-cultural Approaches
- PERSONALITY TESTS IN SOUTH AFRICA
- Introduction
- THE DEVELOPMENT OF THE SOUTH AFRICAN PERSONALITY
- Introduction
- Item Development for the SAPI
- ITEM FORMATTING IN PERSONALITY QUESTIONNAIRES
- Introduction
- Defining Block- and random- iteming
- VALIDITY AND RELIABILITY
- Validity
- Reliability
- CHAPTER SUMMARY
This was done because "reliability is not usefully separated from the idea of validity in examining the appropriateness of test use [because] the concept of reliability is directly related to construct meaning (validity)". The determination of validity and reliability deals with the provisions of Article 8 of the Employment Equality Act (No. 47 of 2013). When the data were analyzed and significant results related to the objective of this study were obtained, the researcher reported the findings in the results section of this study, which reflects the results of the EFA and validity studies.
RESEARCH DESIGN AND METHODS
INTRODUCTION
RESEARCH PARADIGM/ PHILOSOPHY
- Introduction
RESEARCH DESIGN
- Introduction
- Research Strategy
SAMPLING
- Introduction
- sampling method and size
- Sampling selection
DATA COLLECTION
- Introduction
- Measuring Instrument
DATA ANALYSIS
- Introduction
- Record, store and coding of the data gathered
- data preparation
- Factor analysis
RELIABILITY
ETHICS IN RESEARCH
- Introduction
CHAPTER SUMMARY
RESEARCH RESULTS
INTRODUCTION
DATA PREPARATION/SCREENING
FACTORIAL ANALYSIS
- Conscientiousness
- Emotional Stability
- Extraversion
- Facilitating
- Integrity
- Intellect
- Openness
- Relationship Harmony
- Soft-Heartedness
RELIABILITY
CHAPTER SUMMARY
CONCLUSIONS, LIMITATIONS AND
INTRODUCTION
This chapter presents a discussion of the main findings and conclusions (based on the results presented in chapter 4) in relation to the research objectives set out in the first chapter. The limitations and implications of the main findings are also presented, along with recommendations for future research regarding item format and structural fit and the SAPI project in general.
ACHIEVEMENT OF THE RESEARCH OBJECTIVES
- General Objective
- Specific Objectives
Moreover, all other differences were insignificant with respect to the four aspects listed above as points of comparability, when considering the sample size of the study and the number of items within the SAPI. Therefore, the findings indicated that the random response set can also be used for the SAPI as the differences between the results of the two response sets were minor. Ortner (2004) identified a German article by Rost and Hoberg (1997) that stated that no differences in the construct validity of the factor structure were identified when either block or random-response designs were used.
This discussion is integrated with a discussion of the analysis of factor structure, including qualitative interpretability, item agreement, and logical interpretability. The second specific research objective was to determine whether the block or random item format best replicated, or was best representative of, the preliminary qualitative personality factor structure of the SAPI. Replication of the conceptual qualitative SAPI model within the block and random-response sets showed that four of the groups replicated the same number of factors in both block and random-response sets.
In evaluating the reliability of the two response sets, specific cut-off points were used (see Chapter 3) to ensure clearer interpretation and classification of scores. In the final step of the analysis, the Cronbach alpha coefficients of all nine clusters were identified for both the random and block response sets (see Chapter 4). For the purpose of the study, reliability scores were classified as high if they were equal to or above 0.80 and as acceptable if they were equal to or above 0.60.
Eight of the nine groups for both the random- and block-response sets had reasonable internal consistency. The analysis showed that the block response set had higher overall Cronbach alpha coefficients for all but two of the clusters (Relationship Harmony, which showed the same Cronbach value for both response sets and Gentleness). This was done by looking at the qualitative interpretability (themes), item agreement and logical interpretability of the factor loadings and comparing them.
LIMITATIONS OF THE RESEARCH STUDY
The Cronbach alpha coefficients for the block response sequence ranged from 0.54 to 0.92, while the Cronbach alpha coefficients for the random response sequence ranged from 0.47 to 0.90. For both the random and block response sets, the Emotional Stability cluster had a Cronbach value below 0.60 and was therefore considered unreliable. Based on the analysis in chapter 4 (see section 4.3), it has been established that the block answer set shows clearer themes and logical interpretability per factor than the random answer set.
Although all the participants from the first strategy completed informed consent forms, the use of open sessions in the second strategy ensured that participation was completely voluntary. Second, the sample may have experienced a language barrier when completing the assessment, as only 6.1% of respondents who completed the block SAPI and 8.8% of respondents who completed the random SAPI listed their home language as English. However, the administration of the SAPI in English should not be a deciding factor, as the private nursing education policies specifically state that English is their official language.
The third limitation relates to the fact that limited empirical research has been conducted on block and random items (Franke, 1997), particularly in the South African context. Valchev (2012) identified a lack of current knowledge about personality in South Africa; underlines the need for an investigation into the order of goods for SAPI. In addition, a limitation has been discovered regarding the availability of research on the positioning of items within the field of personality (Franke, 1997; Laher, 2011).
Therefore, this study provides new knowledge about the development of the SAPI within the South African context. A fourth limitation that emerged during the analysis was that some factors loaded only two or three items, limiting interpretability, reliability, and overall psychometrics. This limitation can be avoided by proper instructions at the start of administration.
IMPLICATIONS OF THE RESEARCH FINDINGS
RECOMMENDATIONS FOR FUTURE RESEARCH ON ITEM FORMATTING
- Recommendations pertaining to this study
With regard to the fourth limitation discussed in section 5.3 regarding the factors with less than three items, it is advised to remove these factors in future research for practical reasons (Costello & Osborne, 2005; Labuschagne, 2010). This recommendation is based on the fact that factors with less than three items provide insufficient information about a specific construct, and do not contribute significantly to the overall reliability of the construct. It has been included to address the issues of reliability and the empirical, statistical and psychometric properties of the SAPI.
Second, attention should also be paid to the Extraversion and Intellect random clusters, as the factor analysis showed unsatisfactory statistical and empirical pattern matrices. The random Intellect analysis showed that two of the factors were presented with only one item. Additional analysis has been performed to improve the output of the analysis, with the researcher pushing the boundaries.
However, similar results were obtained and therefore results < 0.40 were used for consistency and comparability reasons not only for the block response set, but also for the rest of the SAPI clusters. Additional analysis was performed to improve the output of the analysis, with the researcher setting the cut-off value to < 0.35 (to load more items). Costello and Osborne (2005) noted that if the factor loadings appear disorganized and uninterpretable, as was the case for the Intellect and Extraversion random clusters, this is unlikely to be improved by manipulating the number of factors or factor loading cut-off values, as the problem probably stems from the data.
However, given that this study used descriptive research, allowing comparison between block and randomized outcomes, removing items was not ideal as it would affect the comparability of the formats and thus compromise the reliability of the data. Therefore no additional items were removed; only items that were problematic in both sets of responses were removed as part of the data review process, and this was done specifically for comparability reasons. This recommendation was accepted and promoted for future research with the exception of the factors within the Openness group, namely, Individualism, Traditionalism, and Religiosity, which loaded on both the block response and random response groups.
RECOMMENDATIONS FOR FUTURE RESEARCH ON THE SAPI PROJECT
It is therefore recommended that further research be conducted on these factors, which might allow for the inclusion of items that specifically measure these three factors in depth in the South African context.
CONCLUSION
Fluid Intelligence, Crystallized Intelligence, and the Openness/Intellect Factor. 2005).Cross-cultural generalizability of personality types. The relationship between the five-factor model of personality and job performance for a group of Middle Eastern expatriates. Testing a five-factor model of personality variation among farmers in the Bolivian Amazon.
Structural equivalence and the NEO-PI-R: Implications for the applicability of the five-factor model of personality in an African context.
