Analysis of variance or ANOVA can be used to compare the means between two or more groups of values. 

In the example below, three columns contain scores from three different types of standardized tests:  math, reading, and science.  We can test the null hypothesis that the means of each sample are equal against the alternative that not all the sample means are the same. 

Example Dataset

To perform a single factor ANOVA:

  1. On the XLMiner Analysis ToolPak pane, click Anova:  Single Factor.
  2. Click the Input Range field, then enter A1:C10.
  3. Leave Columns selected for Grouped By, since the data is grouped by column. 
  4. Since the first row contains our column headings, select Labels in First Row selected.
  5. Leave Alpha at the default of 0.05.  This is the level of significance for the hypothesis test.   
  6. Click the Output Range field and enter cell A12.
  7. Click OK. 

Anova: Two-Factor with Replication Pane

The results are shown below. 

ANOVA: Two-Factor with Replication results

Cells C17:E19 show various statistics of each group:  Sum, Average, and Variance. 

Cell F24 contains the p-value for the calculated value of F (in cell E23) found by the Analysis ToolPak.  Notice that the p-value or probability of obtaining an F statistic of 3.44 or larger when the null hypothesis is true is .6650.  Since the p-value is greater than the specified alpha of 0.05, the null hypothesis is accepted.