Name
Title | ||
|---|---|---|
Approximate confidence and prediction intervals for least squares support vector regression. |
Abstract | ||
|---|---|---|
Bias-corrected approximate 100(1-α)% pointwise and simultaneous confidence and prediction intervals for least squares support vector machines are proposed. A simple way of determining the bias without estimating higher order derivatives is formulated. A variance estimator is developed that works well in the homoscedastic and heteroscedastic case. In order to produce simultaneous confidence intervals, a simple Šidák correction and a more involved correction (based on upcrossing theory) are used. The obtained confidence intervals are compared to a state-of-the-art bootstrap-based method. Simulations show that the proposed method obtains similar intervals compared to the bootstrap at a lower computational cost. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/TNN.2010.2087769 | IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council |
Keywords | Field | DocType |
homoscedasticity,least squares support vector regression,bootstrap based method,variance,computational cost,kernel-based regression,confidence interval,regression analysis,homoscedastic case,heteroscedasticity,heteroscedastic case,prediction intervals,least squares approximations,least squares support vector machines,bias,support vector machines | Least squares,Confidence distribution,Pattern recognition,Homoscedasticity,Robust confidence intervals,Prediction interval,CDF-based nonparametric confidence interval,Artificial intelligence,Confidence and prediction bands,Statistics,Confidence interval,Mathematics | Journal |
Volume | Issue | ISSN |
22 | 1 | 1941-0093 |
Citations | PageRank | References |
32 | 1.70 | 10 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kris De Brabanter | 1 | 32 | 1.70 |
| De Brabanter, J. | 2 | 32 | 2.04 |
| Johan A. K. Suykens | 3 | 635 | 53.51 |
| Bart De Moor | 4 | 5541 | 474.71 |