Question

This week you read about different ways of exploring data in order to display and describe that data. If you were presented with an unfamiliar dataset, what are the first exploratory steps you would take to get familiar with the dataset and decide how to display the data?

Answer 1

The unknown data is often encountered by several analysts. The exact nature of the data or what the purpose of collecting the data was is often unknown.

Hence in these scenarios, exploratory data analysis is performed. In exploratory data analysis, the data is studied using several methods.

These methods include developing a hypothesis based on certain patterns evident in the data, visualizing the data using graphical tools. The graphical tools can vary in several ways and include plots like histograms, pie charts, etc. What tool to use depends on the nature of the data as to whether it is categorical or numerical; and within numerical whether it is discrete or continuous.

Based on these tools, the pattern in the data can be visualized and this can now be used to frame a statistical study.