Premium
A Method of Positional Quality Control Testing for 2 D and 3 D Line Strings
Author(s) -
ArizaLópez Francisco Javier,
RodríguezAvi José
Publication year - 2015
Publication title -
transactions in gis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.721
H-Index - 63
eISSN - 1467-9671
pISSN - 1361-1682
DOI - 10.1111/tgis.12117
Subject(s) - string (physics) , parametric statistics , line (geometry) , statistical hypothesis testing , sample (material) , quality (philosophy) , set (abstract data type) , product (mathematics) , control (management) , sample size determination , mathematics , algorithm , combinatorics , computer science , statistics , physics , artificial intelligence , geometry , mathematical physics , programming language , quantum mechanics , thermodynamics
This article presents a positional quality acceptance control method for 2 D and 3 D line strings based on a statistical hypothesis test. Two statistical models are applied together: a B inomial M odel is applied over a B ase M odel. By means of the B ase M odel the method can be applied to any parametric or non‐parametric error model. The B ase M odel represents the hypothesis about the error behavior. The B inomial M odel is fixed and consists of counting the number F of fail events in a sample of a determined size. The π parameter of the B inomial M odel is derived from the B ase M odel by means of a desired tolerance. By comparing the probabilities associated to F and π a statistical acceptance/rejection decision is achieved. This method allows us to know and control the user's and producer's risk of acceptance/rejection. An example using a 2 D line string data set from a commercial product is presented. The extension of the method to the 3 D line string case is also presented. In order to facilitate the application of the method, some tables linking π with F and the control sample sizes are presented.