Skip to McMaster Navigation Skip to Site Navigation Skip to main content
McMaster Logo McMaster logo

Leading the Way on Fundamental Issues

Though every research project is unique, certain fundamental issues often arise when it comes to working with, and interpreting big, data. Broadly speaking, the issues can be grouped under the headings of creation, collection, management, transformation, and analysis.

McMaster is already known for its interdisciplinary and inter-sectoral collaborations and MacData will help further this reputation by promoting an integrated approach around all aspects of data creation, collection, management, transformation, and analysis.

Expandable List

This relates to AI, machine learning, statisitcal learning, and statistics, and includes visualization as well as analysis techinques. In addition to the utilization of existing advanced techniques, the development of new analytical tools is crucial to permit the analysis of large, complex and evolving data types.

This relates to the collection of structured and unstructured measures and data that is manually or electronically captured. When concerned about creation of data, the skills and expertise needed relates to the development or integration of methodologies for capturing information, for example, how to improve survey taking, the development of recording devices, and the capturing information.

This relates to work done to get access to data that have been collected by third party sources (for example, businesses or governments). Activities related to collection include database development, the tracking of data use, and activities related to data collection and gaining access to data.

This relates to things like innovations tied to data storage (for example, server capacity, cloud solutions, secure housing of data), data archiving, data curation, and data access. The efficient use of servers and network infrastructures, the development of firmware, software, and processes all relate to data management.

This relates to the use of measures from primary and secondary data sources to create data sets to permit analysis. Before data can be analyzed, many issues must be addressed, including assessing the data quality, identifying rules for data development, transformation of information, liking of records, de-identification and encryption of records/measures, and archiving.