Article Text
Statistics from Altmetric.com
Introduction
Sometimes our work goes deep into our brain. A bit like Don Quixote and the windmills, a sick statistical mind looks at Sagrada Familia, Barcelona's iconic church (figure 1), and sees its resemblance to spline basis functions. Then one wonders…would it work? Maybe Gaudí's masterpiece still has some hidden secrets we have yet to unveil. In this paper, basis functions approximating the shape of Sagrada Familia were used to smooth the daily mortality counts in Barcelona during the year 2009, as a fun way to give a flavour on how parametric spline methods work. All this was done with a wisp of hope for serendipitously discovering a revolutionary new statistical tool.
Sagrada Familia church in Barcelona (left panel) and estimated overlaid curves (right panel).
Methods
Time series studies of air pollution often use basis functions (eg, natural splines) to smooth the data and adjust for seasonal and temporal trends.1 Splines are actually used to capture non-linear associations in …
Footnotes
Competing interests None declared.
Provenance and peer review Commissioned; externally peer reviewed.
Request Permissions
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.