BsplineQuantReg - 'Constrained Quantile Regression with Cubic B-Splines'

Quantile regression with cubic B-splines under monotonicity and convexity constraints using the Karlin-Studden SOCP formulation. The method is described in Abbes (2026) <doi:10.5281/zenodo.17427913>. This R implementation is intended for demonstration and prototyping; all B-spline and polynomial functions have been rewritten for consistency. A faster version written in 'Python' is available at <https://github.com/alexandreabbes/Constrained-Quantile-Regression-with-cubic-splines>.