Extraction, Manipulation, and Visualization: A different take on introducing Exploratory Data Analysis
Data science and statistics education is in increasing demand as decisions based on data analysis are rising in prevalence throughout the technology-powered workforce. Education facilitates the exploration of critical data science concepts and provides students with employable and useful skills. As an ever-evolving field, data science has many instruction processes with different focuses and outcomes. One such instruction process is focused on the progression of data extraction, manipulation, and visualization (EMV). EMV differs from other data processes such as exploratory data analysis (EDA) and is characterized by its focus on cleaning and organizing the data before visualization. We will provide two examples of how to implement EMV within the classroom. The first example is utilizing EMV to understand the population of California counties. We then extended this within the second example to implement EMV on the population of counties in California, Oregon, and Washington. This presentation describes and argues for an EMV approach to teaching data science to help students learn techniques for deriving accurate, useful, and insightful conclusions from data