Describing the Relationship Between Two Variables

Scatter Diagrams

Scatter diagrams are graphical tools used to visualize the relationship between two quantitative variables. Each point on the diagram represents a pair of values for the two variables.

• Explanatory (Predictor) Variable: Plotted on the horizontal (x) axis. This variable is used to explain variability in the response variable.

• Response Variable: Plotted on the vertical (y) axis. This variable is the outcome of interest.

• Interpretation: The pattern of points can suggest the type (linear or nonlinear) and strength of the relationship.

• Example: A scatter diagram of students' study hours (x) versus exam scores (y) may show a positive association.

Correlation and the Linear Correlation Coefficient

The linear correlation coefficient, denoted by r, measures the strength and direction of the linear relationship between two quantitative variables.

• Properties of r:

  • r ranges from -1 to 1.

  • r = 1: Perfect positive linear relationship.

  • r = -1: Perfect negative linear relationship.

  • r = 0: No linear relationship.

  • The absolute value |r| indicates the strength of the association; values closer to 1 or -1 indicate stronger relationships.

  • r is similar in interpretation to the slope (rise/run), but it is a standardized measure.

• Formula for r:

  • Where and are the data values, and are the means, and and are the standard deviations of x and y, respectively.

• Important Note: Correlation does not imply causation. A strong correlation does not mean that changes in one variable cause changes in the other.

Response vs. Explanatory Variables

Understanding the roles of variables is crucial in statistical analysis:

• Explanatory Variable (Predictor): The variable that is manipulated or categorized to observe its effect on the response variable.

• Response Variable: The outcome or variable being measured.

• Example: In a study of the effect of temperature (x) on ice cream sales (y), temperature is the explanatory variable and sales is the response variable.

Least-Squares Regression Line

The least-squares regression line is the line that best fits the data in a scatter diagram, minimizing the sum of the squared vertical distances (residuals) between the observed values and the line.

• Equation of the Line:

  • : Predicted value of the response variable

  • : Slope of the line

  • : y-intercept

• Formulas:

  • Slope:

  • Intercept:

• Residual: The difference between the observed value and the predicted value:

• Interpretation: A smaller residual indicates a better fit for that data point.

• Example: If the regression line is , and for , the observed is 295, then the predicted $y$ is . The residual is .

Coefficient of Determination (R2)

The coefficient of determination, denoted , measures the proportion of the variance in the response variable that is explained by the explanatory variable using the regression line.

• Formula:

• Interpretation: An value of 0.85 means that 85% of the variability in the response variable is explained by the regression model.

Correlation vs. Causation

It is important to distinguish between correlation and causation:

• Correlation: Indicates a statistical association between two variables.

• Causation: Implies that changes in one variable directly cause changes in another.

• Note: A strong correlation does not imply a causal relationship. Other factors (confounding variables) may be involved.

Summary Table: Key Concepts in Bivariate Analysis

Additional info:

• Contingency tables are referenced as being covered in later chapters (Chapters 11 and 12), which deal with categorical data analysis.

• Some formulas and steps were inferred and expanded for clarity and completeness.