Groups are defined by rows and columns

Prism organizes data for two-way ANOVA differently than do most other programs.

Prism does not use grouping variables. Instead, use rows and columns to designate the different groups (levels) of each factor. Each data set (column) represents a different level of one factor, and each row represents a different level of the other factor.

Setting up the data table

From the Welcome (or New Data Table and Graph) dialog, choose the Grouped tab.

Entering raw data

Create a Grouped table with enough subcolumns to hold the maximum number of replicates you have.

In the example above, the two rows encode the two levels of one factor (serum starved vs. normal culture) and the three data set columns encode the three levels of the other factor (cell line).

Entering averaged data

If you have already averaged your replicates in another program, you can choose to enter and plot the mean and SD (or SEM) and n. If your data has more than 256 replicates, this is the only way to enter data into Prism for two-way ANOVA.

Note that repeated measures ANOVA requires raw data. This is not a quirk of Prism, but fundamental to repeated measures analyses. So if you enter mean, sample size and SD or SEM, you'll only be able to do ordinary (not repeated measures) ANOVA.

Entering single values

If you only have one value for each condition, create a Grouped table and choose to enter a single Y value (no subcolumns). In this case, Prism will only be able to compute ordinary (not repeated measures) ANOVA, and will assume that there is no interaction between the row and column factor. It cannot test for interaction without replicates, so simply assumes there is none. This may or may not be a reasonable assumption for your situation.

Run the ANOVA

1.From the data table, click on the toolbar.

2.Choose Two-way ANOVA from the list of grouped analyses.

3. On the first tab (Experimental Design), define whether or not your experimental design used repeated measure.  Optionally name the grouping variables that define the rows and columns.

4. On the second (Multiple Comparisons) and third (Options) tab, choose multiple comparisons.

Prism can't handle huge data sets

Prism 7 cannot run two-way ANOVA with huge data sets and presents an message telling you so (Prism 6 would crash or freeze). How huge is huge? Really big! The details  depends on whether or not your data are repeated measures, but does not depend on which multiple comparisons tests you chose (if any).

No matching.  Regular two-way ANOVA (not repeated measures)

Prism cannot analyze tables where:  number of rows * number of columns > 16,384

Each column represents a different time point, so matched values are spread across a row

Prism cannot analyze tables where:   (number of rows)2 * number of columns * number of subcolumns * (number of columns + number of subcolumns) > 268,435,456

Each row represents a different time point, so matched values are stacked into a subcolumn

Prism cannot analyze tables where: number of rows * (number of columns)2 * number of subcolumns * (number of rows + number of subcolumns) > 268,435,456

Repeated measures by both factors

Prism can handle any table you can enter.