AWS Certified Machine Learning – SpecialtyExploratory Data AnalysisMedium

A financial institution is analyzing credit card transaction data to detect fraudulent activities. They want to identify the strength and direction of the linear relationship between 'transaction_amount' and 'transaction_frequency_per_day' to see if unusual combinations might indicate fraud. Which statistical measure is most appropriate for this analysis?

  1. AANOVA
  2. BPearson correlation coefficient
  3. CChi-squared test
  4. DT-test
Show answer & explanation

Correct answer: B. Pearson correlation coefficient

The Pearson correlation coefficient measures the linear relationship between two continuous variables, 'transaction_amount' and 'transaction_frequency_per_day'. Its value ranges from -1 to 1, indicating the strength and direction of the correlation, which is precisely what the institution needs.

Why the other options are wrong

  • A. ANOVA (Analysis of Variance) is used to compare means across three or more groups, not to measure the correlation between two continuous variables.
  • C. The Chi-squared test is used for categorical variables to assess independence or goodness-of-fit, not for measuring linear relationships between continuous variables.
  • D. A T-test is used to compare the means of two groups, not to determine the correlation between two continuous variables.

Pearson Correlation Coefficient

A statistical measure that quantifies the linear relationship between two continuous variables. It ranges from -1 (perfect negative correlation) to +1 (perfect positive correlation), with 0 indicating no linear correlation.

  • Measures strength and direction of linear association.
  • Requires both variables to be continuous.
  • Sensitive to outliers; assumes normality for inference.

Memory trick: Pearson: 'Pairs' of continuous variables, 'R'elationship.

More Exploratory Data Analysis questions