Borders Scanning Algorithm to Solving Total Least Trimmed Squares Estimation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F12%3A00199818" target="_blank" >RIV/68407700:21340/12:00199818 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Borders Scanning Algorithm to Solving Total Least Trimmed Squares Estimation
Original language description
The Total Least Squares is one of the most widely use method for data analysis, where both dependent and independent variables are observed with random errors. If data set contains outliers, the robustified version of TLS such as mixed Least Trimmed Squares - Total Least Trimmed Squares method is used. The disadvantage of this method is absence of exact algorithm that can find solution of the estimation in real time for data sets with large number of observations. In this paper we introduced the BSA algorithm for LTS-TLTS and compare it with BAB algorithm. It is the first introduction to this method for such a problem and only first results from simulation study are shown.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
CEP classification
BA - General mathematics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů