Example of Comparisons

An electronics design engineer studies the effect of operating temperature and three types of face-plate glass on the light output of an oscilloscope tube. The engineer has performed Fit General Linear Model and then uses Comparisons to determine whether the mean differences between pairs of glass types are statistically significant and to estimate those differences.

  1. Open the sample data, LightOutput.MTW.
  2. Choose Stat > ANOVA > General Linear Model > Comparisons.
  3. From Response, select LightOutput.
  4. Under Type of comparison, select Pairwise.
  5. Under Method, select Tukey.
  6. Under Choose terms for comparisons, double-click GlassType.
  7. Click OK.

Interpret the results

The interval plot of the differences shows that the mean difference between the light output for GlassType 1 and GlassType 2 is statistically significant because the interval labeled "2-1" does not contain zero.

The grouping information table in the session window output also indicates that this difference is statistically significant because the two groups do not share a letter. This table shows that the mean for GlassType 1 is 1087.33 and the mean for GlassType 2 is 1035.00.

Comparisons for LightOutput

Tukey Pairwise Comparisons: GlassType

Grouping Information Using the Tukey Method and 95% Confidence GlassType N Mean Grouping 1 9 1087.33 A 3 9 1054.67 A B 2 9 1035.00 B Means that do not share a letter are significantly different.
By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy