The explanation of the procedure is divided into two sections: the former regarding the statistical estimator of the intensity (based on the intersection with an independent motion invariant test fibre process) and the estimation of its variance, the latter regarding the learned detector of the intersections from a digital image.
THE STATISTICAL ESTIMATOR OF THE INTENSITY AND THE ESTIMATION OF ITS VARIANCE
A point statistical estimator
is said to be consistent if it approaches the parameter being estimated as the sample size increases.
It is probably easier to operationalize a statistical value definition using a statistical estimator
Other new sections are mixture distributions, non-homogeneous Poisson processes, sufficient statistical estimators
and the linear exponential family, Bayesian analysis and conjugate prior distributions, nonparametric statistical methods, and graphical methods.
We provide an overview of stabilization methods for point processes and apply these methods to deduce a central limit theorem for statistical estimators of dimension.
Rather than review these applications, our goal here is twofold: (i) review the essential theory underpinning stabilization and (ii) employ the techniques to describe the limit theory for statistical estimators of dimension.
Two types of statistical estimators are used: mean-per-unit estimators and ratio estimators.
Both types of statistical estimators have been used to estimate bycatch in shrimp trawl fisheries.