What is it about?
We highlighted that Monte Carlo method is a primary tool for deriving solutions to complex (or analytically intractable) problems. Here, two problems were presented. First, how can we find the optimal number of Monte Carlo experiments for quality control purpose? Second, how do we obtain the probability levels of a consecutive statistical test procedure? Furthermore, we highlight the p-value approach to multiple outlier detection as well as we show how to improve the statistical power of a outlier test by the Monte Carlo method.
Featured Image
Why is it important?
A large sets of observations are being recorded or sampled. It is nearly impossible that such datasets are free from outliers. Thus, it is important to identify outlying observations that may lead to model misspecification, biased parameter estimation, and incorrect results.
Perspectives
Despite the countless contributions made over the last 50 years, there is continuing research on the topic, which paves the way for further investigations. In addition to the Monte Carlo, new tools have become available, such as genetic algorithms, swarm intelligence, simulated annealing, fuzzy approaches, and metaheuristic algorithms, to handle datasets contaminated by outliers. Their potential for outlier treatment is not yet fully exploited in geodesy.
Vinicius Rofatto
Universidade Federal de Uberlandia
Read the Original
This page is a summary of: A half-century of Baarda’s concept of reliability: a review, new perspectives, and applications, Survey Review, November 2018, Taylor & Francis,
DOI: 10.1080/00396265.2018.1548118.
You can read the full text:
Resources
Contributors
The following have contributed to this page
