← AIAP Topic CoursesAll programsHomeSearch
AIAP Topic Courses·Data Analysis·06:35

Bivariate Analysis: Correlation, Scatter Plots, and a Live Excel Crosstab

Data Analysis trainer (unnamed) Marketing-analytics practitioner; runs four AI data tools on one e-commerce orders dataset
▶LMS lesson
← PreviousUnivariate Analysis: One Column at a Time
Lesson 6 of 11 in Data Analysis
Next →Multivariate Analysis: Regression, PCA, Clustering, and a Three-Variable Pivot

The short version

  1. Two variables at once. Pearson correlation from -1 to +1: study hours vs exam score at r = 0.8 is strong positive; AI computes correlation matrices over hundreds of pairs. Scatter plots show slope and outliers (the student who studied 40 hours and scored low) (0:00-0:02).
  2. Categorical pairs use a cross-tabulation. Live Excel: Insert > PivotTable, platform in rows, order status in columns, count of status as values - cancelled, pending, shipped, damaged per platform. 'Which city has the most kurta orders' is bivariate (0:02-0:06).

At a glance, three clicks deep

Skim here first: the closed row is the glance, open is the study card with the key points and timestamps, and the ↓ link drops to that concept's full write-up below.

01Bivariate analysis: correlation for numbers, crosstabs for categoriesCorrelation + scatter;›

Correlation + scatter; crosstab via pivot.

Correlation and scatter (0:00-0:02)

Crosstab and pivot demo (0:02-0:06)

↓ Full write-up of this concept

The concepts in full

01

Bivariate analysis: correlation for numbers, crosstabs for categories

Numbers pair up in a scatter plot. Categories pair up in a pivot table. That is the whole of bivariate analysis.

Pearson correlation: +1 perfect positive, -1 perfect negative, 0 independent; r = 0.8 for study time vs score. Scatter plots confirm direction and expose outliers. Cross-tabulation counts combinations of categories (gender vs product type). PROCEDURE in Excel: Insert > PivotTable; 'e-commerce platform' to Rows; 'order status' to Columns; drag order status to Values as a count. Result: per-platform counts of each status. Any two-variable question - city with the most kurta orders - is bivariate.

Why it matters

The second rung of the prompt vocabulary, and the first hands-on step.

This idea elsewhereparallelKairos pivot-table case

Tools referenced

ToolCoverageMomentContext
Microsoft ExceldemonstratedPivotTable crosstab

Action items

    Resources mentioned

    Resources
    • docLesson page on the platform

    Extraction notes

    This page was built from an auto-generated transcript, which garbles product and people's names. Those were corrected silently in everything above and logged here for transparency. The warnings flag claims that were true on the recording day but change fast.

    Transcript corrections applied

    The transcript saysThe trainer actually means
    Charge GPT / Chart GPT / ChargeGPDChatGPT
    cloud / Cloud AIClaude
    Mishou / Misho / MISOMeesho
    main dot com / mail dot comMake.com

    True on recording day — verify before relying

    ← PreviousUnivariate Analysis: One Column at a TimeNext →Multivariate Analysis: Regression, PCA, Clustering, and a Three-Variable Pivot