Causality analysis techniques can be used for fault diagnosis in industrial processes. Multiple causality analysis techniques have been shown to be effective for fault diagnosis [1]. Comparisons of some of the strengths and weaknesses of these techniques have been presented in literature [2,3]. However, there are no clear guidelines on which technique to select for a specific application. These comparative studies have not thoroughly addressed all the factors affecting the selection of techniques. In this paper, these two techniques are compared based on their accuracy, precision, automatability, interpretability, computational complexity, and applicability for different process characteristics. Transfer entropy and Granger causality are popular causality analysis techniques, and therefore these two are selected for this study. The two techniques were tested on an industrial case study of a plant wide oscillation and their features were compared. To investigate the accuracy and precision of Granger causality and transfer entropy, their ability to find true connections in a simulated process was also tested. Transfer entropy was found to be more precise and the causality maps derived from it were more visually interpretable. However, Granger causality was found to be easier to automate, much less computationally expensive, and easier to interpret the meaning of the values obtained. A decision flow was developed from these comparisons to aid users in deciding when to use Granger causality or transfer entropy, as well as to aid in the interpretation of the causality maps obtained from these techniques. (C) 2019 Elsevier Ltd. All rights reserved.