A limited number of culturally appropriate personality assessments are currently available in South Africa due to the mass importation of psychometric assessments in the past. The South African Personality Inventory (SAPI) project was initiated as a result of the growing demand for culturally appropriate assessment instruments as well as the change in South African legislation regarding psychometric testing (Section 8 of the Employment Equity Act, No. 47 of 2013). The SAPI project aims to identify universal and culture-specific personality traits for all 11 language groups in South Africa. The project’s central research objectives are to develop a personality instrument that complies with South African legislation, meets all the regular criteria for adequate assessment as formulated in psychology, and is relevant for South-African institutions. The SAPI project consists of multiple studies that are aimed at enabling the use of the SAPI within the open market in order to allow practitioners to validly assess personality within the South African context. This study forms part of the quantitative body of work within the SAPI project and builds on the literature of the SAPI, resulting in a more acceptable instrument. The primary objective of this study was to determine whether block– or random-item sequencing provides the best factorial replication within the framework of the SAPI. 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 at multiple private nursing education institutions. Both the block– and random-SAPI versions consisted of 262 closed-ended questions that were administered using a pen-and-paper methodology. The data preparation indicated that four block- and 19 random-items were problematic and could not be included in the analysis. After removing the problematic items, a strategy was used to formulate a conclusion pertaining to the superior item sequence. This strategy included performing an exploratory factor analysis on each of the nine factors for both the random- and block-response sets. The factor loadings were analyzed, interpreted and presented separately. The researcher looked at the most plausible sub-cluster structure for each of the nine factors, followed by assessing the structural similarity between the two response sets by comparing them to the conceptual qualitative personality structure to identify which response set was more closely related. The reliability of all the factors and sub-clusters for both response sets were also analysed and reported. The final conclusion was derived from an overall comparison made between the block- and random response sets. By utilizing the strategy it was determined that the block response set provided for a better structurally and factorially valid framework when applied to the conceptual personality structure of the SAPI. However, upon closer inspection, the differences between the block- and random response sets seem to be trivial. The findings therefore indicate that the random response set can also be used as only minor differences were noticed when compared to the block response set. / Dissertation (MCom)--University of Pretoria, 2014. / tm2015 / Human Resource Management / MCom / Unrestricted

依據「多層次混合試題反應理論」與「隨機試題混合模型」，本研究提出「混合試題與受試者模型」。本研究旨在評估此模型在不同樣本數、不同試題差異功能的試題數下，偵測試題差異功能的表現，以及其參數回復性情形。研究結果顯示，「混合試題與受試者模型」在樣本數大、試題差異功能試題數較多之情境下，具有正確的參數回復性，能正確判斷出試題是否存在試題差異功能，且具有良好的難度估計值，並能將樣本正確地分群，其也與「隨機試題混合模型」的估計表現頗為相近。建議未來可將「混合試題與受試者模型」應用於大型教育資料庫相關研究上，並加入其他變項後進一步探討。 / Drawing upon the framework of the multilevel mixture item response theory model and the random item mixture model, the study attempts to propose one model, called the mixture items and examinees model(MIE model). The purpose of this study was to assess the respective performances of the model on different sample-sizes and differential item functioning (DIF) items. Particularly, the study assessed the model performances in the detection of DIF items, and the accurate parameters recovery. The results of the study revealed that with large sample-sizes and more DIF items, the MIE model had the good parameters recovery, the accurate detection of the DIF items, the good estimate of the item difficulty, and the accurate classifications of the sub-samples. These model performances appeared similar to those of the random item mixture model. The findings suggest that future studies should apply the MIE model to the analyses on large-scale education databases, and should add more variables to the MIE model.