In our emerging era of Big Data, a basic literacy in key concepts in handling Big Data is becoming part of the essential skill set needed for work in laboratory settings, whether within academia or industry. Basic Big Data literacy involves an intuitive understanding of the fundamental differences between Big Data and 'small data.' The two main differences are the nature of the exploitable information which Big Data my contain and the methods used to exploit that information.<br/><br/>The primary difference between Big Data and small data (other than the size of the data sets) is that Big Data are highly multivariate in nature. It is this multivariate character which provides the potential to discover valuable relationships which may not be readily apparent to the human eye-brain combination. The discovery and exploitation of the relationships encoded in Big Data is accomplished primarily by empirical modeling.<br/><br/>Fortunately, it should be possible to incorporate material involving multivariate data into conventional undergraduate curricula in a natural way. It is similarly reasonable to adjust curricula to include coverage of the proper approach to empirical modeling. This presentation will cover the significant elements comprising an intuitive understanding of multivariate data together with a discussion of the importance a disciplined approach which is required for successful development and employment of multivariate empirical modeling. Familiarity with these significant elements and with this modeling discipline is proposed as a useful set of curricula goals.

Key concepts in handling big data; suggested goals for undergraduate curricula

255th National Meeting (2018)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.