Question
During EDA, a data scientist wants to look for patterns, such as linearity, in the data. Which of the following plots should the data scientist use?
- A. Violin
- B. Box-and-whisker
- C. Scatter Correct
- D. Q-Q
Explanation
A scatter plot shows one variable against another, so it reveals relationships such as linearity, curvature and clusters between them. Violin and box-and-whisker plots summarize the distribution of a single variable, and a Q-Q plot compares a variable's distribution with a theoretical one such as the normal distribution rather than showing the relationship between two variables.