In addition to the scree test, you can use the Kaiser method to determine the number of principal components. In this method, the selection criteria retains eigenvalues greater than 1
. In this recipe, we will demonstrate how to determine the number of principal components using the Kaiser method.
Ensure that you have completed the previous recipe by generating a principal component object and save it in the variable, swiss.pca
.
Perform the following steps to determine the number of principal components with the Kaiser method:
- First, you can obtain the standard deviation from
swiss.pca
:
> swiss.pca$sdev Output [1] 1.6228065 1.0354873 0.9033447 0.5592765 0.4067472
- Next, you can obtain the variance from
swiss.pca
:
> swiss.pca$sdev ^ 2 output [1] 2.6335008 1.0722340 0.8160316 0.3127902 0.1654433
- Select components with a variance above
1
:
...