predint

Prediction intervals for cfit or sfit object

collapse all in page

Syntax

ci = predint(fitresult,x)
ci = predint(fitresult,x,level)
ci = predint(fitresult,x,level,intopt,simopt)
[ci,y] = predint(...)

Description

ci = predint(fitresult,x) returns upper and lower 95% prediction bounds for response values associated with the cfit object fitresult at the new predictor values specified by the vector x. fitresult must be an output from the fit function to contain the necessary information for ci. ci is an n-by-2 array where n = length(x). The left column of ci contains the lower bound for each coefficient; the right column contains the upper bound.

example

ci = predint(fitresult,x,level) returns prediction bounds with a confidence level specified by level. level must be between 0 and 1. The default value of level is 0.95.

ci = predint(fitresult,x,level,intopt,simopt) specifies the type of bounds to compute.

Observation bounds are wider than functional bounds because they measure the uncertainty of predicting the fitted curve plus the random variation in the new observation. Non-simultaneous bounds are for individual elements of x; simultaneous bounds are for all elements of x.

[ci,y] = predint(...) returns the response values y predicted by fitresult at the predictors in x.

Note

predint cannot compute prediction intervals for non-parametric fittypes such as Interpolant, Lowess, and Spline.

Examples

collapse all

Open Live Script

Calculate and plot observation and functional prediction intervals for a fit to noisy data.

Generate noisy data with an exponential trend.

x = (0:0.2:5)';
y = 2*exp(-0.2*x) + 0.5*randn(size(x));

Fit a curve to the data using a single-term exponential.

fitresult = fit(x,y,'exp1');

Compute 95% observation and functional prediction intervals, both simultaneous and nonsimultaneous. Nonsimultaneous bounds are for individual elements of x; simultaneous bounds are for all elements of x.

p11 = predint(fitresult,x,0.95,'observation','off');
p12 = predint(fitresult,x,0.95,'observation','on');
p21 = predint(fitresult,x,0.95,'functional','off');
p22 = predint(fitresult,x,0.95,'functional','on');

Plot the data, fit, and prediction intervals. Observation bounds are wider than functional bounds because they measure the uncertainty of predicting the fitted curve plus the random variation in the new observation.

subplot(2,2,1)
plot(fitresult,x,y), hold on, plot(x,p11,'m--'), xlim([0 5]), ylim([-1 5])
title('Nonsimultaneous Observation Bounds','FontSize',9)
legend off
   
subplot(2,2,2)
plot(fitresult,x,y), hold on, plot(x,p12,'m--'), xlim([0 5]), ylim([-1 5])
title('Simultaneous Observation Bounds','FontSize',9)
legend off

subplot(2,2,3)
plot(fitresult,x,y), hold on, plot(x,p21,'m--'), xlim([0 5]), ylim([-1 5])
title('Nonsimultaneous Functional Bounds','FontSize',9)
legend off

subplot(2,2,4)
plot(fitresult,x,y), hold on, plot(x,p22,'m--'), xlim([0 5]), ylim([-1 5])
title('Simultaneous Functional Bounds','FontSize',9)
legend({'Data','Fitted curve', 'Prediction intervals'},...
       'FontSize',8,'Location','northeast')

Figure contains 4 axes objects. Axes object 1 with title Nonsimultaneous Observation Bounds, xlabel x, ylabel y contains 4 objects of type line. One or more of the lines displays its values using only markers These objects represent Data, Fitted curve. Axes object 2 with title Simultaneous Observation Bounds, xlabel x, ylabel y contains 4 objects of type line. One or more of the lines displays its values using only markers These objects represent Data, Fitted curve. Axes object 3 with title Nonsimultaneous Functional Bounds, xlabel x, ylabel y contains 4 objects of type line. One or more of the lines displays its values using only markers These objects represent Data, Fitted curve. Axes object 4 with title Simultaneous Functional Bounds, xlabel x, ylabel y contains 4 objects of type line. One or more of the lines displays its values using only markers These objects represent Data, Fitted curve, Prediction intervals.

Input Arguments

collapse all

Function of which you want to find the prediction intervals, specified as a cfit or sfit object.

fitresult must be an output from the fit function to contain the necessary information for ci.

Predictor values used to compute the upper and lower prediction bounds of fitresult, specified as a vector.

Confidence level of the prediction bounds, specified as a positive scalar between 0 and 1.

Type of bounds, specified as either:

  • 'observation' — Bounds for a new observation (default)

  • 'functional' — Bounds for the fitted curve

Type of bounds, specified as either:

  • 'off' — Non-simultaneous bounds (default)

  • 'on' — Simultaneous bounds

Output Arguments

collapse all

Upper and lower prediction bounds, returned as an array of size n-by-2, where n = length(x).

Response values predicted by fitresult at the predictors in x, returned as a vector.

Limitations

Prediction intervals cannot be computed for fit objects with constraint points specified. The software will return NaN values.

Version History

Introduced in R2013a

See Also

| |

Topics