The wave of knowledge loss and attrition that organisations face in a world of layoffs, retirements, staff turnover and mergers gave rise to this study. The purpose of the paper is to describe the research methodology that was followed, which focuses on theoretical and empirical research, including multiple multivariate analysis techniques to develop a model that would explain the factors that could enhance or impede tacit knowledge retention. An understanding of the research methodology can assist other researchers in utilising this process for future model development and it could assist organisations in coping with a world of losing knowledge by retaining critical tacit knowledge. The preliminary literature review on knowledge retention revealed the theoretical approach to be followed, namely a multi-disciplinary approach focusing on knowledge management, organisational behaviour and organisational development. A theoretical model was developed that identifies the organisational and behavioural factors to be considered when addressing the issue of knowledge loss. This theoretical model focused on human input factors considering knowledge loss risks and behavioural threats that could cause knowledge loss and strategy implementation risks. A quantitative empirical research paradigm using the survey method was followed to determine the extent to which these factors impact knowledge retention. The survey was conducted electronically and on paper in the water supply industry. The exploratory factor analysis technique was used to explore the factor structure underlying the variables. The internal reliability of the variables in the newly proposed factor model was determined. Nine key factors were identified through principle component factor analysis of which knowledge behaviour, leadership and strategy implementation had the highest factor loadings. The next step was to follow a model development strategy using the structural equation modelling (SEM) technique to find the best fitting model. After rigorous model testing three final models were compared. The regression model that forms part of the SEM process confirmed that there are relationships between most dimensions, which are in line with the theory. A further multiple regression analysis was performed to determine the degree to which different dimensions predict knowledge retention. In summary it can be concluded that the research methodology chosen for this research study, underpinned by SEM, can be utilised to firstly confirm the influencing factors of knowledge retention. Secondly SEM enables the development of a theoretically justified new model to determine the relationship between strategy implementation, knowledge behaviour and knowledge retention.
