Hybrid statistical and machine learning modeling of cognitive neuroscience data.

The nested data structure is prevalent for cognitive measure experiments due to repeatedly taken observations from different brain locations within subjects. The analysis methods used for this data type should consider the dependency structure among the repeated measurements. However, the dependency assumption is mainly ignored in the cognitive neuroscience data analysis literature. We consider both statistical, and machine learning methods extended to repeated data analysis and compare distinct algorithms in terms of their advantage and disadvantages. Unlike basic algorithm comparison studies, this article analyzes novel neuroscience data considering the dependency structure for the first time with several statistical and machine learning methods and their hybrid forms. In addition, the fitting performances of different algorithms are compared using contaminated data sets, and the cross-validation approach. One of our findings suggests that the GLMM tree, including random term indices indicating the location of functional near-infrared spectroscopy optodes nested within experimental units, shows the best predictive performance with the lowest MSE, RMSE, and MAE model performance metrics. However, there is a trade-off between accuracy and speed since this algorithm is required the highest computational time.

Integrating cognition in the laboratory with cognition in the real world: the time cognition takes, task fidelity, and finding tasks when they are mixed together.

It is now possible for real-life activities, unfolding over their natural range of temporal and spatial scales, to become the primary targets of cognitive studies. Movement toward this type of research will require an integrated methodological approach currently uncommon in the field. When executed hand in hand with thorough and ecologically valid empirical description, properly developed laboratory tasks can serve as model systems to capture the essentials of a targeted real-life activity. When integrated together, data from these two kinds of studies can facilitate causal analysis and modeling of the mental and neural processes that govern that activity, enabling a fuller account than either method can provide on its own. The resulting account, situated in the activity's natural environmental, social, and motivational context, can then enable effective and efficient development of interventions to support and improve the activity as it actually unfolds in real time. We believe that such an integrated multi-level research program should be common rather than rare and is necessary to achieve scientifically and societally important goals. The time is right to finally abandon the boundaries that separate the laboratory from the outside world.