An interaction is the failure of one variable to produce the same effect on the output response at different levels of another input variable. In other words, the strength or the sign (direction) of an effect is different depending on the value (level) of some other variable(s). An interaction can be either positive or negative.

In the Interactions tab you can view the effect of an input variable on an output response at varying levels of other input variables in an interaction plot or interaction table.

To change the format interactions are displayed, click (Interactions Plot) or (Interactions Table) above the Channel selector.

For the design matrix below, interactions are calculated as:

Interaction of X on Y is then (0 - 800) = -800

Interaction of X on Y is then (-600 - 200) = -800

Design Matrix

Note that interactions are symmetric; that is:

Interaction XY = effect of (X) on effect of (Y) = effect of (Y) on effect of (X)

In the Linear Effects tab you can view the effects of input variables on output responses, ignoring the effects of other input variables.

To change the format linear effects are displayed, click (Linear Effects Plot) or (Linear Effects Table) above the Channel selector.

Linear Effects Plot

Linear effects are plotted by drawing a line between the average value of the output response when the input variable is at its lower bound and the average value of the output response when the input variable is at its upper bound.

Linear Effects Table

Linear effects are calculated using a linear regression model for the normalized input variable ranges of [-1, 1]. The linear effect value of input variable x on output response f(x, y) doubles the coefficient a1 of the regression model for f(x)=a0+a1*x. That is, if the linear regression model for the output response f(x) is ao+a1*x where a1 is equal to 400.0 and x is between -1.0 and 1.0, then the linear effect of the input variable x on the output response f(x,y) is 800.0.

For 2-level design of experiments, linear effect values can also be calculated as the difference between the average output responses when the input variable is at its lower value and when the input variable is at its upper value.

Given a 2-factor, 2-level full factorial DOE matrix over the design space of [0:2] on both parameters as:

Design Matrix

In the Pareto Plot tab the effects of variables on output responses are plotted in hierarchical order (highest to lowest).

Hashed lines with a positive slope indicates a positive effect. If a variable increases, the output response will also increase. Hashed lines with a negative slope indicates a negative effect. Increasing the variables lowers the output response.

Pareto Plot Settings

Access settings for the Pareto plot from the menu that displays when you click (located above the Channel selector).