A study finds r=−0.85 between hours of TV watched per day and exam scores. Interpret this value.
Example 3
medium
Scatterplot shows data tightly clustered around a flat horizontal trend. Estimate r.
Example 4
hard
Calculate r for the data (1,2),(2,3),(3,5),(4,4),(5,6).
Example 5
challenge
Anscombe's quartet shows four datasets with identical mean, SD, and r=0.816 but radically different shapes. What lesson does this teach about r?
Practice Problems
Try each one, then open the solution to compare your method.
Example 1
medium
If r=0.92, what is the coefficient of determination r2, and what does it mean?
Example 2
easy
A study finds a correlation coefficient of r=0.88 between height and arm span. Describe the direction and strength of the linear relationship.
Example 3
easy
A correlation coefficient is r=+1. What does this mean?
Example 4
easy
What does a correlation of r=−1 indicate?
Example 5
easy
A correlation of r=0 means what about the linear relationship?
Example 6
easy
Which is stronger: a correlation of r=−0.9 or r=+0.6?
Example 7
easy
As study hours increase, test scores tend to increase. What sign is the correlation?
Example 8
easy
As a car's age increases, its resale value tends to decrease. What sign is the correlation?
Example 9
easy
Can you compute a correlation between eye color and favorite number?
Example 10
easy
Ice cream sales and drowning incidents both rise in summer, giving r=+0.8. Does ice cream cause drowning?
Example 11
medium
A scatterplot shows points tightly clustered along an upward line. Estimate whether ∣r∣ is closer to 0, 0.5, or 1.
Example 12
medium
Two variables have r=0.3. Is this a strong relationship? Explain.
Example 13
medium
A data set's x and y values are perfectly linearly related by y=2x+1. What is r?
Example 14
medium
If every y value is multiplied by 3 (a positive constant), how does r between x and y change?
Example 15
medium
A relationship is described by y=−0.5x+4 exactly. What is r?
Example 16
medium
A study finds towns with more firefighters have more fire damage (r=+0.7). Why is concluding 'firefighters cause damage' wrong?
Example 17
medium
Data points are (1,1),(2,2),(3,3),(4,4). What is the correlation r?
Example 18
medium
Two variables show a strong U-shaped (curved) relationship. Why might r be near 0?
Example 19
medium
Data points are (2,10),(4,20),(6,30). What is the correlation r?
Example 20
challenge
Points are (1,5),(2,4),(3,3),(4,2),(5,1). Without full computation, state r and justify.
Example 21
challenge
Correlation between height and weight is r=0.8 in adults. A researcher claims height 'explains' weight. What two cautions apply?
Example 22
challenge
Variable A correlates with B at r=0.9, and B correlates with C at r=0.9. Must A and C be strongly correlated?
Example 23
easy
If r=−0.95, describe the direction and strength of the linear relationship.
Example 24
easy
Hours studied and exam scores have r=0.65. Is the relationship positive or negative? Strong, moderate, or weak?
Example 25
medium
If r=0.7, compute the coefficient of determination and interpret it.
Example 26
medium
A linear model y^=3+2x fits data perfectly. What are r and r2?
Example 27
medium
Data shows r=0.9 between shoe size and reading ability among children aged 5–12. Why might this be misleading as evidence of causation?
Example 28
medium
Data points are (1,10),(2,7),(3,4),(4,1). What is r?
Example 29
medium
A study reports r=0.7 between exercise frequency and happiness. Can you conclude exercising more will make a specific person happier?
Example 30
medium
Why can r be near 0 even for a tight non-linear (e.g., parabolic) relationship?
Example 31
hard
Compute r for the data (1,1),(2,2),(3,3),(4,4),(5,100).
Example 32
hard
A researcher reports r=0.95 from a sample of size 4. Why is this fragile evidence of a real relationship?
Example 33
hard
Data (0,0),(1,1),(2,4),(3,9),(4,16) follow y=x2. Is r near 0 or near 1?
Example 34
hard
If rXY=0.6 and rYZ=0.6, what is the minimum possible value of rXZ?
Example 35
challenge
A study finds r=0.85 between math scores and music scores in 1000 students. Does this prove studying music improves math?
What to focus on
Core idea:Correlation describes how two variables move together; it does not by itself prove cause.
Common stuck point:The procedure for correlation is the easy part; the trap is saying correlation proves causation. Asking "Do the dots show a direction and tightness of pattern?" first is what keeps a correct-looking calculation from being attached to the wrong concept.
Ask yourself:Do the dots show a direction and tightness of pattern?
Concept recap
Correlation measures the strength and direction of the linear relationship between two quantitative variables, ranging from −1 to +1.
Two correlated variables are like two dancers. With positive correlation, when one steps forward the other usually steps forward too; with negative, one steps back as the other steps forward. The tighter they stay in step, the closer r is to 1 or −1. Dancing in step does not tell you who is leading, or whether both are just following the music.