Scree plot
Topic of Principal component analysis, part of Statistical learning
Scree plot
| Type | Topic |
| Taught in | Principal component analysis |
| Part | Statistical learning |
A plot of the eigenvalues, the component variances, in decreasing order. A bend after which they level off is an informal guide to how many principal components to keep; it can be ambiguous, and it does not validate a predictive model.
In Principal component analysis
A scree plot offers a visual heuristic: look for a point after which additional eigenvalues contribute relatively little. The cumulative percentages on this correlation are about 39, 62, 75, 83, 89, 93, 97 and 100. A bend can be ambiguous or absent, and it does not validate a predictive model. For prediction, select the number of components using a validation set or an inner cross-validation. Keep the final test set untouched. Using the same observations both to choose the number of components and to assess the fit leaves no untouched assessment sample.
Used in
See also
Eigenvalues and eigenvectors · Variance · Principal component directions and scores · Principal component directions · Scaling · Principal components by Lagrange multipliers · Reconstruction from principal components · Choosing the number of principal components