An investigation into the internal structure of the unit performance construct as measured by the performance index (PI)

• Main Author: Henning, Roline
• Other Authors: Theron, C.C.
• Format: Others
• Language: en_ZA
• Published: Stellenbosch : Stellenbosch University 2012
• Subjects: Organizational effectiveness; Organizational effectiveness > Measurement; Performance > Measurement; Dissertations > Industrial psychology; Theses > Industrial psychology
• Online Access: http://hdl.handle.net/10019.1/52679

Assignment (MA)--University of Stellenbosch, 2002 === ENGLISH ABSTRACT: The responsibility for the performance of any organisational unit ultimately lies with the leadership of the unit. Given this perceived pivotal role of leadership in work unit performance, the ultimate objective is to capture the nature of the presumed relationship between leadership and unit performance in a comprehensive structural model. To validate such a leadership model, however, requires an explanation of the manner in which the unit performance dimensions affect each other. Spangenberg and Theron (2002b) developed a generic, standardized unit performance measure (PI) that encompasses all the unit performance dimensions for which the unit leader could be held responsible. The objective of this paper is to investigate the internal structure of the PI in order to establish the inter-relationships between the eight unit performance latent variables. The PI consists of 56 questions covering eight dimensions. The validation sample consisted of 304 completed PI questionnaires. However, after imputation 273 cases with observations on all 56 items remained in the validation sample. Item analysis and dimensionality analysis was performed on each of the sub-scales using SPSS. Thereafter, confirmatory factor analysis was performed on the reduced data set using LISREL. The results indicated satisfactory factor loadings on the measurement model. Acceptable model fit was achieved for the measurement model. Subsequently, the structural model was tested using LISREL. The results provided statistics of good fit. Only four hypotheses failed to be corroborated in this study. Conclusions were drawn from the results obtained and suggestions for further research are made. === AFRIKAANSE OPSOMMING: Die prestasie van enige organisatoriese werkeenheid is die uiteindelike verantwoordelikheid van die leierskap van die eenheid. Gegewe hierdie waargenome sleutelrol van leierskap in werkeenheidprestasie, is die uiteindelike doelwit om die aard van die veronderstelde verwantskap tussen leierskap en eenheidprestasie in 'n omvattende strukturele model vas te lê. Die validering van so 'n leierskapmodel vereis egter 'n uiteensetting van die wyse waarop die eenheidprestasie-dimensies mekaar onderling beïnvloed. Spangenberg en Theron (2002b) het 'n generiese, gestandaardiseerde eenheidprestasie-meetinstrument (PI) ontwikkel wat al die eenheidprestasie-dimensies insluit waarvoor die leier van die eenheid verantwoordelik gehou kan word. Die doel van hierdie studie is om ondersoek in te stel na die interne struktuur van die PI ten einde die inter-verwantskappe tussen die agt eenheidprestasie latente veranderlikes vas te stel. Die PI bestaan uit 56 vrae wat die agt dimensies dek. Die validasiesteekproef bestaan uit 304 voltooide PI vraelyste. Na vervanging van ontbrekende waardes is die validasiesteekproef egter gereduseer tot 273 gevalle met waarnemings op al 56 items. Item-ontleding en dimensieanalise is op elk van die sub-skale met behulp van SPSS gedoen. Daaropvolgend is bevestigende faktor-analise op die verkorte datastel gedoen met behulp van LISREL. Die passingstatistieke het hier aanvaarbare resultate opgelewer. Vervolgens is die strukturele model met behulp van LISRELgetoets. Die resultate het hier bevredigende passingstatistieke gelewer. Daar kon vir slegs vier hipoteses nie steun gevind word in die studie nie. Op grond van die resultate is daar tot bepaalde gevolgtrekkings gekom en daar word aanbevelings vir verdere navorsing gemaak.