Subscribe Bookmark RSS Feed



May 29, 2014

Assessing Normality (OPG)

Topics: Assessing normality for a continuous (quantitative) variable.

Category: Probabilities and Distributions

JMP features: Analyze > Distribution, Normal Quantile Plot.


Open One-Page Guide (PDF)

Watch short video:

I found this article easy to apply to my real life data, thank you.


Glad to hear it, thanks!


So, we do not need to calculate the residual before the normality test.

I ask this question because I found these steps (

 Analyze the residuals to check the assumption of normality

  1. In the Fit Y by X platform, select JMP: Save > Save Standardized
  2. The result appears in the data table as a new column/variable labeled "Y" Standardized by "X". These are the residuals.
  3. In the data table select JMP: Analyze > Distribution
  4. In the Analyze Distribution dialog window select the residuals column/variable.
  5. Study the histogram and stem-plot for symmetry.
  6. Note the skewness under JMP: Summary Statistics.
  7. Perform a Shapiro-Wilks test for normality by selecting JMP: Continuous Fit > Normal.
  8. Under Fitted Normal select JMP: Goodness of Fit.

Btw, now it's clear for me.


Article Labels
Article Tags