Pearson Correlation Analysis

Pearson correlation analysis measures the strength and direction of the linear relationship between two continuous variables with a coefficient r ranging from -1 to +1.

피어슨 상관분석은 두 연속형 변수 사이 선형관계의 강도와 방향을 -1에서 +1 사이의 상관계수 r로 측정하는 방법이다.

How do I measure how strongly two continuous variables are linearly related?

두 연속형 변수가 선형적으로 얼마나 강하게 관련되어 있는지 어떻게 측정하나요?

Pearson correlation analysis quantifies the linear association between two continuous variables with r and tests whether it differs from zero. It fits roughly linear relationships without extreme outliers; for monotonic or ordinal relationships, Spearman's rank correlation is used instead.

When to use Pearson Correlation Analysis

• Two or more continuous variables whose pairwise linear association is of interest
• Building a correlation matrix before regression or factor analysis
• Scatterplots that show a roughly straight-line pattern

When to use something else

• Ordinal data, outliers or curved monotonic relationships; use Spearman's rank correlation
• Controlling for a third variable; use partial correlation

Assumptions and requirements

• Continuous variables measured on paired observations
• Linear relationship
• Approximate bivariate normality for significance tests
• No extreme outliers

What the analysis reports

• Correlation coefficient r
• p-value
• 95% confidence interval for r
• Correlation matrix
• Scatterplot

How to report it

[Variable 1] was positively correlated with [Variable 2], r([df]) = [value], p = [value].

Related methods

• Spearman Rank Correlation
• Partial Correlation
• Simple Linear Regression

Run Pearson Correlation Analysis on Quorant