A hitchhiker’s guide to information theoretical measures in psychology
Niels Van Santen et al.
What the paper says
In psychology, as in other sciences, information theory can be used as a tool to complement more standard regression-based methods of data analysis. It is important to see the potential of information theoretical measures as statistical tools without implying a connection to their origins in communication theory and engineering. The use of these measures may provide us with additional insights due to their sensitivity to non-linear relationships, their flexibility to the mixing of data types, and their more straightforward generalization towards investigating higher-order interactions. We briefly reintroduce information theory and compare several measures such as mutual information and co-information with correlation and regression-based methods for the investigation of variable dependence. • Information theory and psychology have a rich history • Information theoretical measures can be disconnected from information theory • These measures complement variance-based measures of variability and association • They are more general with respect to interpretation and possible data types • There are many extensions towards the investigation of higher-order interactions.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.