Optimal design for smooth supersaturated models

Hugo Maruri-Aguilar (Queen Mary, University of London)

Smooth supersaturated models (SSM) are interpolation models in which the underlying model size, and typically the degree, is higher than would normally be used in statistics, but where the extra degrees of freedom are used to make the model smooth.

I will describe the methodology regarding its application to smooth models over non-standard regions. We perform a two stage design and modelling strategy and apply our methodology in a complex example taken from the literature of soap film smoothing. Time allowing, I will explore the use of smooth models with boundary conditions defined by algebraic expressions.

This is joint work with Ron Bates (Rolls-Royce), Peter Curtis (QMUL) and Henry Wynn (LSE).

Back to event page