Exploratory Data Analysis
Look at data to see what it seems to say.
Uncover underlying structures.
Isolate important variables.
Detect outliers and other anomalies.
Suggest suitable models for conventional statistics.
The term “exploratory data analysis” was introduced by John W. Tukey who in  shows how simple graphical and quantitative techniques can be used to open-mindedly explore data.
Plotting the raw data (e.g., stem-and-leaf diagrams, histograms, scatter plots)
Plotting simple statistics (e.g., mean plots, box plots, residual plots)
Positioning (multiple) plots to amplify cognition
Measures of location or of scale
Shapes of distributions
Exploratory data analysis can help to improve the results of statistical hypothesis...