Validity and Reliability Testing on Train Driver Performance Model Using a PLS Approach

Abstract

Abstract.The purpose of this paper is to explain the assessment of validity and reliability of measured items used in survey research. The structural equation modeling techniques and Partial Least Square (PLS) will be adopted to assess the goodness of measures of constructs used in a model to examine the performance of the Malaysian train drivers. The measurement process involves assessment of construct validity of the items and followed by convergent validity. Then, the composite reliability was assessed with internal consistency measure of Cronbach's alpha. Lastly, discriminant validity was tested to assess the validity of the measurement. The constructs are not supposed to measure other constructs or overlapping constructs. IntroductionHuman performance.Performances are related to the job or task assigned to the operators unless it is conducted fully automatic by machines or robots. But, most of industries still depend on their human operators including railway, where locomotives are still operated by the train drivers.Previously, human factors was left behind and be considered as independent factors with very less contribution to the overall system performance[1]. Researchers conducted their studies on individual variable to measure performance, factors affecting performance and effect of performance; either on individual level or organizational level. Most of them relate one or two variables or factors affecting performance with the effect or consequences of the level of performance.To date, investigations on human performance factors were conducted and influences the overall performance measurement and study ranging from the air traffic control system, design process at the factories, train driving activities and ship navigation [2][3][4][5]. Awareness on importance of human performance studies are increasing and consideration on human performance factors come earlier during design stage.Therefore, the development of human performance will enable the consideration of potentially conflicting task demands in a systematic and structured ways as the earliest stages in a design [6].This study was conducted through survey research method, where it involves the usage of questionnaires and scales. Therefore, this paper will look at the goodness of measures assessment used in the analysis by looking at the validity and reliability. The structural equation modeling techniques and Partial Least Square (PLS) will be adopted to assess the goodness of measures of constructs used in a model to examine the performance of the Malaysian train drivers.

Integrating Embodied Social Presence Theory and Process Virtualization Theory to assess business process virtualizability: The mediating role of embodied co-presence

“…As indicated in Table 3, the results demonstrate that Cronbach's alpha values are above the 0.7 threshold, suggesting acceptable levels of reliability. Similarly, both rho_A and rho_C for CR are above 0.7, and AVE values exceed 0.5 [68,69]. These findings indicate that each measurement variable exhibits high internal consistency, which is crucial for ensuring the reliability of the constructs within our model.…”

Job Motivation, Burnout and Turnover Intention during the COVID-19 Pandemic: Are There Differences between Female and Male Workers?

“…We evaluated the convergent validity of the factors using the average variance extracted AVE, considering 0.50 as critical value [ 91 ]. From the results obtained, we verified the convergent validity of the BO, IM, EM and TI; the variance extracted is greater than 0.50.…”