Lesson 6 of 6 · All lessons in this module
  1. Parametric vs non-parametric tests, and correlation hypotheses
  2. The t-test for a Pearson correlation
  3. Sample size, p-values and many correlations at once
  4. The Spearman rank correlation testVideo lesson
  5. Contingency tables and the chi-square test of independenceVideo lesson
  6. Interpreting the result: standardized residuals and mosaics

Lesson 6 of 6 · 12 min

Interpreting the result: standardized residuals and mosaics

Rejecting independence tells you the classifications are related; standardized residuals tell you which cells are responsible and in which direction.

In short

  • Standardized residual (also Pearson residual) = (Oij−Eij)/Eij (O_{ij}-E_{ij})/\sqrt{E_{ij}} .
  • Positive: more observations than independence predicts; negative: fewer.
  • Each squared residual is that cell’s contribution to χ2 \chi^2 , so the squared residuals sum to χ2 \chi^2 .
  • A mosaic pictures the table: rectangle widths and heights show proportions, and shading shows the size and sign of the residuals.
  • Choosing the test: Pearson t (continuous, normal), Spearman (non-normal, outliers or ranks), chi-square (categories).

Unlock this lesson free for 7 days

Create a free account to get 7 days free: every lesson, video and flashcard, and the question bank. No card needed.