On Robust Testing for Normality of Error Terms in Regression Models
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F15%3A43906564" target="_blank" >RIV/62156489:43110/15:43906564 - isvavai.cz</a>
Result on the web
<a href="http://mme2015.zcu.cz/downloads/MME_2015_proceedings.pdf" target="_blank" >http://mme2015.zcu.cz/downloads/MME_2015_proceedings.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
On Robust Testing for Normality of Error Terms in Regression Models
Original language description
Testing for normality of error terms constitutes one of the most important steps of regression model verification and validation, because failure to assess non-normality of the regression residuals may lead to incorrect results since significant deviations from normality can substantially affect the performance of usual statistical inference techniques. Thus, in the majority of cases of relevant regression analysis normality of error terms is expected. However, this is not true in many practical situations. While OLS estimator is known to be very sensitive to outliers, the robust regression estimator (e.g. Least Trimmed Squares, LTS) is known not to be unduly affected by the presence of outliers. The aim of this paper is to present and discuss the trade-off between power and robustness of selected classical and robust normality tests of error terms in regression models. For this purpose we use OLS and LTS residuals from linear regression models with various distributed dependent variab
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
BB - Applied statistics, operational research
OECD FORD branch
—
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Mathematical Methods in Economics 2015: Conference Proceedings
ISBN
978-80-261-0539-8
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
749-754
Publisher name
Západočeská univerzita
Place of publication
Plzeň
Event location
Cheb
Event date
Sep 9, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—