Quantile sheet estimator with shape constraints
classification
📊 stat.ME
keywords
estimatorquantileproposedsheetnon-crossingpropertiesquantilesalgorithm
read the original abstract
A quantile sheet is a global estimator for multiple quantile curves. A quantile sheet estimator is proposed to maintain the non-crossing properties for different quantiles. The proposed estimator utilizes SCOP: shape-constrained P-spline to enforce the non-crossing properties directly in construction. A local GCV parameter tunning algorithm is used for fast estimation results. Data simulation shows the proposed method and existing competitors can recover the underlying quantiles with comparable mean square error.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.