Test yourself on Scatter Graphs with exam style questions, marked instantly.
Flashcards that come back just before you would forget them.
A revision plan that remembers what you know and shows what to do next.
See which topics you have nailed and which need another look.
Quiz yourself on Scatter GraphsGet your flashcardsBuild my revision planTrack my progressDiscovering Relationships in Data
A teacher wonders: "Do students who study more hours get better test scores?" To investigate, she collects data from 20 students about their study time and test results. But looking at two lists of numbers doesn't reveal patterns easily.
Enter scatter graphs! By plotting each student as a point (study hours on x-axis, test score on y-axis), she can instantly see if there's a relationship. Do the points trend upward? That suggests more study leads to better scores!
Key Facts About Scatter Graphs
- Purpose: Show relationships between two variables
- Correlation: How closely two variables are related
- Positive correlation: As one increases, the other increases
- Negative correlation: As one increases, the other decreases
- No correlation: No clear relationship between variables
- Line of best fit: Shows the general trend in the data
- Outliers: Points that don't fit the general pattern
Understanding Correlation
Types of Correlation
1. Strong Positive Correlation
- Points lie close to an upward sloping line
- As x increases, y increases
- Example: Height vs. shoe size
2. Weak Positive Correlation
- General upward trend but points are scattered
- Relationship exists but with lots of variation
- Example: Study time vs. test scores (many other factors)
3. Strong Negative Correlation
- Points lie close to a downward sloping line
- As x increases, y decreases
- Example: Car age vs. value
4. Weak Negative Correlation
- General downward trend but points are scattered
- Example: TV watching time vs. fitness level
5. No Correlation
- Points show no clear pattern
- No relationship between the variables
- Example: Shoe size vs. IQ
Types of Correlation Examples
Drawing Lines of Best Fit
Method for Drawing the Line
- Plot all points accurately on the graph
- Ignore outliers when considering the trend
- Draw a straight line that best represents the trend
- Balance the line so roughly equal numbers of points are above and below
- Make the line long enough to be useful for predictions
Using Lines of Best Fit for Predictions
Interpolation
Predicting values within the range of your data.
Example: If the line shows that 5 hours study gives 75% score, this is interpolation.
Extrapolation
Predicting values outside the range of your data.
Example: Using the line to predict what score someone would get with 12 hours study (if your data only goes up to 10 hours).
Warning: Extrapolation is less reliable - relationships may change outside the measured range.
Exam Tips for Scatter Graphs
- Choose appropriate scales - use most of the grid space
- Label axes clearly with variable names and units
- Plot points accurately - use a sharp pencil and read coordinates carefully
- Identify correlation type - strong/weak and positive/negative/none
- Line of best fit should be straight and balance points above/below
- Ignore outliers when drawing the line of best fit
- Extend the line appropriately for making predictions
- Be cautious with extrapolation - state that it's less reliable
Advanced Applications and Considerations
Identifying Outliers
Outliers are points that don't fit the general pattern. They may indicate:
- Measurement errors
- Exceptional cases
- Different underlying relationships
- Important anomalies worth investigating
Correlation vs. Causation
Important: Correlation does not prove causation!
- Correlation: Variables change together
- Causation: One variable causes the change in another
- Example: Ice cream sales and drowning deaths are correlated (both increase in summer), but ice cream doesn't cause drowning!
Factors Affecting Correlation Strength
- Sample size: Larger samples often show clearer patterns
- Measurement accuracy: More precise measurements show stronger correlation
- Range of values: Wider range often shows correlation better
- External factors: Other variables can mask or enhance relationships
Real-World Applications
- Medical: Drug dosage vs. effectiveness
- Business: Advertising spend vs. sales
- Education: Attendance vs. grades
- Science: Temperature vs. chemical reaction rate
- Sports: Training time vs. performance
- Economics: Unemployment vs. crime rates
Limitations of Scatter Graphs
- Only show relationships between two variables
- Don't show causation
- Non-linear relationships may be missed
- Time-based patterns not clear
- Can be affected by outliers
Make this stick
Signing in gives access to all PrepWise features.