1. Learn about various metrics that can be used to evaluate Total Data Quality (TDQ), at each stage in the TDQ framework.
2. A quality concept map should be created that tracks the relevant aspects of TDQ for a specific application or data source.
3. Consider the relative trade-offs among quality aspects, relative cost and practical constraints that are imposed by a specific project or study.
4. Find the right software and other tools to compute the various metrics.
5. Understanding metrics that can both be calculated for found/organic and designed data.
6. Use the metrics to analyze real data, and interpret the resulting values using a TDQ perspective.
This specialization aims to provide more information on the Total Data Quality framework and help learners understand the details of data quality before they can be used for data analysis. It is the goal of this specialization to help learners incorporate data quality evaluations into their projects as an essential component. We are eager to share knowledge about data quality with all learners, including data scientists and quant analysts who have not received sufficient training in the first steps of the data science process, which focuses on data collection and evaluation. If the data collected/collected are not of sufficient quality, then a thorough knowledge of statistical analysis techniques and data science techniques will not be of any benefit to a quantitative research project.
This specialization will concentrate on the first steps of any scientific investigation that uses data. It will include generating and gathering data, understanding the source of the data, evaluating its quality, and taking steps towards maximizing the data's quality before performing any statistical analysis or using data science techniques to answer research queries. This will mean that there will not be much material on data analysis, which is covered in many other Coursera specializations. This specialization will focus on understanding and maximising data quality before analysis.
