XLSTAT: Levene and Bartlett tests on variances in Excel

 

Dataset for Example

The data are extracted from the Iris example, used in several of our tutorials [Fisher M. (1936), The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics, 7, 179 -188] and correspond to 150 Iris flowers, described by their petal width and the corresponding species.

Three different species have been included in this study: setosa, versicolor and virginica.

Our goal is to test if variance of the petal width is identical across species or not.

The same data are displayed in two alternative formats accepted by XLSTAT: either you have one column with the petal widths, and one column with the species, or you can split the data into three columns, one per species.

Setting Up

• Open XLSTAT.
• Click on the Parametric test menu and select the k-sample comparison of variances feature:

• Once you've clicked on the button, a dialog box appears.

In the General tab:

• In the Data format field, select One column per variable. Interpret the format as having one column for all petal widths and a second column for the corresponding species. 
• Check the Levene's test option.
• Select the Median method, as it is generally more robust and recommended over the Mean option.

Note: XLSTAT offers two formats to select the data. Either all the numerical data are in one column, and a second column corresponds to the sample descritors, or you have the different samples split into as many columns as there are samples.

• Click on the OK button to launch the computations.
• The results are displayed on a new Excel sheet.

Interpreting the Results

The first results displayed are the descriptive statistics for the various samples. Then the results of the tests are displayed.

The two tests agree that one should reject the null hypothesis that the variance of the petal widths is identical for the three samples.