The Kernel Estimation in Biosystems Engineering
Esperanza Ayuga Téllez, Mª Angeles Grande Ortiz, Concepción González García, Angel Julián Martín Fernández, Ana Isabel García García
In many fields of biosystems engineering, it is common to find
works in which statistical information is analysed that violates
the basic hypotheses necessary for the conventional forecasting
methods. For those situations, it is necessary to find alternative
methods that allow the statistical analysis considering those
Non-parametric function estimation includes methods that fit a
target function locally, using data from a small neighbourhood
of the point. Weak assumptions, such as continuity and
differentiability of the target function, are rather used than “a
priori” assumption of the global target function shape (e.g.,
linear or quadratic).
In this paper a few basic rules of decision are enunciated, for the
application of the non-parametric estimation method. These
statistical rules set up the first step to build an interface usermethod
for the consistent application of kernel estimation for
not expert users. To reach this aim, univariate and multivariate
estimation methods and density function were analysed, as well
as regression estimators. In some cases the models to be applied
in different situations, based on simulations, were defined.
Different biosystems engineering applications of the kernel
estimation are also analysed in this review.