Scatter Plots
This type of graph shows the relationship between two quantitative variables.
Scatter plot
This line models the general trend of data points in a scatter plot.
The line of best fit
This statistic measures the strength and direction of a linear relationship.
The correlation coefficient
A residual is found by subtracting this from the actual value.
The predicted value
This set includes the minimum, Q1, median, Q3, and maximum.
The five-number summary
When graphing a scatter plot, this variable belongs on the x-axis.
Independent variable
The goal of a line of best fit is to minimize these values.
Residuals
The correlation coefficient always falls between these two values.
−1 and 1
A positive residual means the actual data point is located where relative to the line?
Above the line
This value separates the lower 25% of the data from the rest.
Q1
A scatter plot where points trend upward from left to right shows this type of relationship.
Positive relationship
In the equation y=mx+b, this parameter represents the rate of change.
m / the slope
A correlation coefficient close to 0 indicates this type of relationship.
Weak or no linear relationship
If a residual is zero, this describes the data point’s location.
On the line
The median represents this percentile.
The 50th percentile
If points are randomly scattered with no clear pattern, the relationship is described this way.
No relationship/correlation
A line of best fit should have roughly this many points above and below it.
About half
If the correlation coefficient is −0.85, the relationship is best described this way.
A strong negative correlation
Large residuals may indicate this feature in the data.
An outlier
The difference between Q3 and Q1 is called this.
The interquartile range (IQR)
This feature of a scatter plot helps determine whether a linear model is reasonable to use.
The overall pattern or trend of the data
This is one reason a data point might not lie close to the line of best fit.
Natural variability, an outlier, or measurement error
This important idea explains why correlation alone cannot prove cause and effect.
Correlation does not imply causation
Residuals are used to judge how well this type of model fits the data.
A linear model
The five-number summary is most commonly displayed using this graph.
A box plot