Data Forest logo
Home page  /  Glossary / 
Scatter Plot

Scatter Plot

A scatter plot is a type of data visualization used to display the relationship between two quantitative variables. Each point on a scatter plot represents a pair of values, plotted along two Cartesian axes (horizontal and vertical). The position of each point is determined by the values of the variables being analyzed, with one variable defining the x-axis and the other the y-axis. Scatter plots are fundamental tools in exploratory data analysis, allowing for a quick visual examination of potential correlations, trends, and patterns within data.

Characteristics of a Scatter Plot

  1. Axes and Coordinates:
    • The x-axis (horizontal) and y-axis (vertical) of a scatter plot represent the two variables being compared. Data points are positioned based on their values along these axes.  
    • Each point, or marker, represents an individual observation, where the x-coordinate corresponds to the value of the independent variable (or feature) and the y-coordinate to the value of the dependent variable (or outcome).
  2. Data Points:
    • The scatter plot consists of numerous points distributed across the graph based on the relationship between the two variables.  
    • Points that are closer together suggest a stronger relationship, while those spread farther apart indicate weaker or no correlation.
  3. Relationship and Correlation:
    • The pattern and distribution of points can reveal the nature of the relationship between variables. Common relationships observed in scatter plots include:    
    • Positive Correlation: As one variable increases, the other also tends to increase. The points slope upward from left to right.    
    • Negative Correlation: As one variable increases, the other tends to decrease, resulting in a downward slope.    
    • No Correlation: The points are scattered randomly, showing no discernible trend.    
    • Non-linear Relationships: In cases where the relationship is more complex, points might form a curve or other non-linear pattern.

Statistical Analysis with Scatter Plots

Scatter plots are often used to visually estimate correlation between variables. Correlation quantifies the strength and direction of a linear relationship:

  • Correlation Coefficient (r): A value between -1 and 1 that measures the linear association between two variables.  
  • When `r = 1`, there is a perfect positive linear relationship.  
  • When `r = -1`, there is a perfect negative linear relationship.  
  • When `r = 0`, there is no linear relationship.

To calculate the correlation coefficient `r` for a sample dataset:

r = Σ [(x_i - x̄)(y_i - ȳ)] / √[Σ (x_i - x̄)² * Σ (y_i - ȳ)²]

Here, x_i and y_i represent individual sample values, and x̄ and ȳ are the sample means for the x and y variables, respectively.

A scatter plot can also support the identification of outliers, which are data points that deviate significantly from the overall pattern.

Regression Line

In scatter plots with a discernible trend, a line of best fit, or regression line, can be drawn to represent the relationship. The simplest form, linear regression, fits a straight line to the data points based on the following equation:

y = mx + b

Where `m` is the slope (rate of change in y for each unit increase in x), and `b` is the y-intercept (the value of y when x is zero).

For a dataset with n observations, the slope (m) and y-intercept (b) are calculated as:

  • m = Σ [(x_i - x̄)(y_i - ȳ)] / Σ (x_i - x̄)²
  • b = ȳ - m * x̄

These equations enable the line to minimize the vertical distances between the points and the line itself, providing the best linear approximation of the relationship.

Scatter plots are extensively used across scientific research, finance, engineering, and machine learning to visually inspect data before formal modeling. They are particularly valuable in Big Data and Data Science, where identifying relationships, trends, and anomalies can inform data cleaning, feature selection, and model development. Scatter plots also lay the groundwork for more sophisticated analyses by offering an intuitive first look at data distributions and relationships.

Data Science
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Latest publications

All publications
Article preview
January 20, 2025
15 min

Corporate Automation: Swapping Excel Chaos for Smart AI Systems

Acticle preview
January 14, 2025
12 min

Digital Transformation Market: AI-Driven Evolution

Article preview
January 7, 2025
17 min

Digital Transformation Tools: The Tech Heart of Business Evolution

All publications
top arrow icon