Exercise 11B: Comparing three groups in Prism

Go to parent GraphPad Prism statistical analyses

I have discovered an invertase-like enzyme that catalyzes the hydrolysis of sugars. In addition to sucrose I suspect that it can bind to other sugars as well. Therefore I have measured the constant kcat/Km of the enzyme on three different sugars: sucrose, maltose and maltotriose, as a measure of the efficiency of the enzyme to convert the substrates. I have repeated the experiment a number of times and the overview of the results can be found in the file Enzyme.csv

The file contains the mean kcat/Km, the standard deviation and the number of times the constant was measured for maltose, sucrose and maltotriose in this order.

Open the file in Prism.
Create a new column table Select to Enter and plot error values already calculated elsewhere Select Mean, SD, N Click Create Import the file Enzyme.csv in the table (the comma is used as a decimal separator) and add column titles:

Are there differences between the sugars ?

Click the Analyze button in the Analyze section of the upper toolbar Select One-way ANOVA (and nonparametric or mixed) in the Column analyses section Click OK The Parameters window contains five tabs: the Experimental design tab: use the default parameters the Repeated measures tab: explanation what repeated measures is, and explanation of the repeated measures tab, use the default parameters in this example the Multiple comparisons tab: select compare the mean of each column with the mean of every other column the Options tab: explanation of the different multiple comparisons tests and the different graphing options the Residuals tab: explanation of residuals plots, tests and how they are calculated Click OK The ANOVA analysis results in two tables. The ANOVA table contains the p-value of the ANOVA Since the p-value is smaller than 0.05 we may reject the null hypothesis and state that there is at least one difference between the groups.

Which sugars are different ?
The second results table that is generated, Multiple comparisons, contains the confidence intervals and results of the pairwise comparisons: Sucrose significantly differs from maltose and maltotriose so we reject the hypothesis that our enzyme is as efficient in breaking down maltose and maltotriose as it is in breaking down sucrose.

As you can see the multiple comparisons do not report exact p-values but asterisks in the summary column:

• * means P ≤ 0.05
• ** means P ≤ 0.01
• *** means P ≤ 0.001
• **** means P ≤ 0.0001

If you want to report exact p-values, then you can ask Prism to calculate them.

Generate exact p-values for the multiple comparisons.
Reanalyze the data Select to perform all pairwise comparisons In the Parameters window go to the Options tab In the Multiple comparisons section select Report multiplicity adjusted P value for each comparison Click OK