Analysis of covariance

Analysis of Covariance (ANCOVA)

Analysis of covariance is an extension is an extension of one way ANOVA to in cooperate a covariate. It is used to test if there is any significant difference between two unrelated groups on a dependent variable.

However, unlike ANOVA it looks for difference in adjusted means. You can use more than one covariate if you wish and covariates are measured on a continuous scale.


  1. Click Analyze – General Linear Model –Univariate

-the univariate dialogue box opens.

  1. Transfer the dependent variable into the Dependent Variable box, the independent variable into the Fixed Factor(s) box and the Covariate into the Covariate(s) by dragging them.
  2. Click on the Option button.
  • Univariate option dialogue box
  1. Transfer the independent variable from the Factors and Factor interactions box to the Display Means for box.
  2. Click on the Compare main effects to activate the Confidence interval adjustment option
  3. From the drop down button in this univariate dialogue box, select the Bonferroni option. Also, select Descriptive statistics and Estimates of size in thee Display area.
  4. Click the Continue button to return to the univariate dialogue box
  5. Click Ok button to generate your output.



The tables generated are Descriptive Statistic, tests of between subject’s effect, estimates and pairwise comparison.

In order to interpret, read along the independent variable row of tests of between subjects and read the value of “sig” column. If the p-value is less than 0.0005 it means there is a statistically significant difference between the adjusted means.

Still stressed from student homework?
Get quality assistance from academic writers!