Main Content


Class: NonLinearModel

Plot of slices through fitted nonlinear regression surface




plotSlice(mdl) creates a new figure containing a series of plots, each representing a slice through the regression surface predicted by mdl. For each plot, the surface slice is shown as a function of a single predictor variable, with the other predictor variables held constant.

Input Arguments


Nonlinear regression model, constructed by fitnlm.


expand all

Plot slices of a fitted nonlinear model.

Load the reaction data and fit a model of the reaction rate as a function of reactants.

load reaction
mdl = fitnlm(reactants,rate,@hougen,[1 .05 .02 .1 2]);

Create a slice plot.


{"String":"Figure Prediction Slice Plots contains 3 axes objects and other objects of type uimenu, uicontrol. Axes object 1 contains 5 objects of type line. Axes object 2 contains 5 objects of type line. Axes object 3 contains 5 objects of type line.","Tex":[],"LaTex":[]}

Drag the X1 prediction line to the right, and observe the change in the predicted response y and in the predicted response curves to X2 and X3.


  • If there are more than eight predictors, plotSlice selects the first five for plotting. Use the Predictors menu to control which predictors are plotted.

  • The Bounds menu lets you choose between simultaneous or non-simultaneous bounds, and between bounds on the function or bounds on a new observation.