Generalized monotonic regression based on B-splines with an application to air pollution data

Abstract

In many studies, it is known that one or more of the covariates have a monotonic effect on the response variable. In these circumstances, standard fitting methods for generalized additive models (GAMs) generate implausible results. A fitting procedure is proposed that incorporates monotonicity assumptions on one or more smooth components within a GAM framework. The algorithm uses the monotonicity restriction for B-spline coefficients and provides componentwise selection of smooth components. Stopping criteria and approximate pointwise confidence bands are derived. The method is applied to the data from a study conducted in the metropolitan area of São Paulo, Brazil, where the influence of several air pollutants like SO(2) on respiratory mortality is investigated.