Seeking relationships in big data: a Bayesian perspective

Abstract

The real purpose of collecting big data is to identify causality in the hope that this will facilitate credible predictivity. But the search for causality can trap one into infinite regress, and thus one takes refuge in seeking associations between variables in data sets. Regrettably, the mere knowledge of associations does not enable predictivity. Associations need to be embedded within the framework of the probability calculus to make coherent predictions. This is so because associations are a feature of probability models, and hence they do not exist outside the framework of a model. Measures of association, like correlation, regression, and mutual information merely refute a preconceived model. Estimated measures of associations do not lead to a probability model; a model is the product of pure thought. This paper discusses these and other fundamentals that are germane to seeking associations in particular, and machine learning in general.

Keywords:

• Association
• Bayesian
• big data
• correlation
• dependence

AMS Subject Classifications:

• C11
• C35
• C46
• C53
• C83

Acknowledgements

The several helpful comments of Michael Edesess and Robert Smythe are gratefully acknowledged. Thanks also go to Boyan Dimitrou, who provided a platform that motivated the writing of this paper.

Notes

No potential conflict of interest was reported by the author.

Additional information

Funding

The work reported in this article was supported by a grant from the City University of Hong Kong [Project No. 9380068].