Scatter Plot: A graph showing relationship between two variables using points
Positive Correlation: Points trend upward (as x increases, y increases)
Negative Correlation: Points trend downward (as x increases, y decreases)
No Correlation: Points scattered randomly with no apparent pattern
Trend Line: Line of best fit showing general direction of data
Outlier: Data point significantly different from others
- Visual Inspection: Look for overall pattern in point distribution
- Correlation Type: Determine positive, negative, or no correlation
- Strength Assessment: Judge how closely points follow a line
- Identify Outliers: Spot unusual data points
- Draw Trend Line: Create line representing main trend
Points: (1, 65), (2, 70), (3, 75), (4, 80), (5, 85), (6, 88), (7, 92), (8, 94), (9, 96), (10, 98)
Positive Correlation: As one variable increases, the other also increases
- Plot the points on a coordinate plane
- Observe the general trend direction
- Determine correlation strength
- Identify any outliers
X-axis: Hours studied, Y-axis: Test scores
Points move from bottom left to top right, indicating positive correlation
Points cluster closely around an imaginary straight line - strong positive correlation
Line rises from left to right, showing direct relationship
This scatter plot shows a strong positive correlation between hours studied and test scores. As study time increases, test scores consistently increase.
• Direction: Upward trend indicates positive correlation
• Strength: Closely clustered points indicate strong correlation
• Interpretation: More study time generally leads to higher scores
Points: (1, 25000), (2, 23000), (3, 21000), (4, 19000), (5, 17000), (6, 15000), (7, 13000), (8, 11000), (9, 9000), (10, 7000)
Negative Correlation: As one variable increases, the other decreases
X-axis: Car age (years), Y-axis: Selling price ($)
Points move from top left to bottom right, indicating negative correlation
Points follow a nearly perfect straight line - very strong negative correlation
Line falls from left to right, showing inverse relationship
This scatter plot shows a very strong negative correlation between car age and selling price. As cars get older, their value decreases predictably.
• Direction: Downward trend indicates negative correlation
• Strength: Perfectly linear points indicate very strong correlation
• Real-world meaning: Cars depreciate over time
Points: (7, 85), (8, 72), (9, 91), (10, 68), (7, 78), (9, 88), (11, 75), (8, 92), (10, 69), (7, 83)
No Correlation: Variables show no predictable relationship
X-axis: Shoe size, Y-axis: Math test scores
Points appear randomly distributed with no clear pattern
Points are scattered widely with no discernible trend - no correlation
No meaningful line can be drawn through the scattered points
This scatter plot shows no correlation between shoe size and math test scores. The variables are independent of each other.
• Pattern: Random scattering indicates no correlation
• Independence: Variables do not influence each other
• Causation: No relationship exists between these variables
Normal points: (70, 150), (75, 170), (80, 190), (85, 210), (90, 230), (95, 250), (100, 270)
Outlier: (80, 350)
Outlier: A data point that differs significantly from other observations
Point (80, 350) deviates significantly from the expected pattern
Most points show positive correlation: higher temperature = higher sales
Line shows positive correlation despite the outlier
Possible reasons: special event, equipment malfunction, or unusual customer behavior
Despite the outlier, there is a strong positive correlation between temperature and ice cream sales. The outlier at (80, 350) may represent an exceptional day due to a special event or error.
• Outlier identification: Points far from main trend cluster
• Trend analysis: Consider outliers separately from main pattern
• Explanation: Outliers often have specific causes worth investigating
Points: (5, 50), (10, 90), (15, 130), (20, 170), (25, 210), (30, 250)
(All values in thousands)
Predictive Analysis: Using trend lines to estimate unknown values
Points show strong positive correlation forming a straight line
For every $1,000 increase in advertising, revenue increases by approximately $8,000
Using the trend line equation, predict revenue for $15,000 advertising
Check if predicted value fits the established pattern
Based on the trend line, spending $15,000 on advertising would generate approximately $130,000 in revenue. The strong positive correlation suggests this prediction is reliable.
• Linear relationship: Consistent rate of change between variables
• Prediction accuracy: Relies on strength of correlation
• Extrapolation caution: Stay within reasonable range of data