Basic Analysis • Bootstrapping • Example of Bootstrapping
Previous
 • 
Next
Example of Bootstrapping
A tire manufacturer wants to predict an engine’s horsepower from the engine’s displacement (in3). The company is most interested in estimating the slope of the relationship between the variables. The slope values help the company predict the corresponding change in horsepower when the displacement changes.
1.
Select Help > Sample Data Library and open Car Physical Data.jmp.
2.
Select Analyze > Fit Y by X.
3.
Assign Horsepower to the Y, Response role.
4.
Assign Displacement to the X, Factor role.
5.
Click OK.
6.
Select Fit Line from the Bivariate Fit red triangle menu.
7.
In the Parameter Estimates report, right-click the Estimate column and select Bootstrap (Select the Bootstrap Option).
Select the Bootstrap Option
The column that you right-click is relevant when the Split Selected Column option is selected. For more information, see Bootstrap Window Options.
8.
Type 1000 for the Number of Bootstrap Samples.
9.
Select Fractional Weights. Leave the other two options selected.
10.
Click OK.
The bootstrap process runs and produces a table with unstacked results for the slope and intercept.
Next, analyze the bootstrapped slope.
11.
Select the unstacked results table, then select Analyze > Distribution.
Tip: Make sure that the correct data table is selected prior to running the Distribution, or else the Bootstrap Confidence Limits report will not appear.
12.
Assign Displacement to the Y, Columns role.
13.
Click OK.
The Distribution report includes the Bootstrap Confidence Limits report (Bootstrap Report).
Bootstrap Report
In this example, the estimate of the slope from the original data is 0.504. For 95% coverage of the bootstrap results, the company can estimate the slope to be between 0.40186 and 0.616. When the displacement is changed by one unit, the horsepower changes by some amount between 0.40186 and 0.616.