A new outlier identification test for method comparison studies based on robust regression
Standard
A new outlier identification test for method comparison studies based on robust regression. / Rauch, Geraldine; Geistanger, Andrea; Timm, Jürgen.
In: J BIOPHARM STAT, Vol. 21, No. 1, 01.2011, p. 151-169.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - A new outlier identification test for method comparison studies based on robust regression
AU - Rauch, Geraldine
AU - Geistanger, Andrea
AU - Timm, Jürgen
PY - 2011/1
Y1 - 2011/1
N2 - The identification of outliers in method comparison studies (MCS) is an important part of data analysis, as outliers can indicate serious errors in the measurement process. Common outlier tests proposed in the literature usually require a homogeneous sample distribution and homoscedastic random error variances. However, datasets in MCS usually do not meet these assumptions. In this work, a new outlier test based on robust linear regression is proposed to overcome these special problems. The LORELIA (local reliability) residual test is based on a local, robust residual variance estimator, given as a weighted sum of the observed residuals. The new test is compared to a standard test proposed in the literature by a Monte Carlo simulation. Its performance is illustrated in examples.
AB - The identification of outliers in method comparison studies (MCS) is an important part of data analysis, as outliers can indicate serious errors in the measurement process. Common outlier tests proposed in the literature usually require a homogeneous sample distribution and homoscedastic random error variances. However, datasets in MCS usually do not meet these assumptions. In this work, a new outlier test based on robust linear regression is proposed to overcome these special problems. The LORELIA (local reliability) residual test is based on a local, robust residual variance estimator, given as a weighted sum of the observed residuals. The new test is compared to a standard test proposed in the literature by a Monte Carlo simulation. Its performance is illustrated in examples.
KW - Analysis of Variance
KW - Clinical Trials as Topic
KW - Confidence Intervals
KW - Evaluation Studies as Topic
KW - Humans
KW - Linear Models
KW - Monte Carlo Method
KW - Research Design
KW - Journal Article
U2 - 10.1080/10543401003650275
DO - 10.1080/10543401003650275
M3 - SCORING: Journal article
C2 - 21191861
VL - 21
SP - 151
EP - 169
JO - J BIOPHARM STAT
JF - J BIOPHARM STAT
SN - 1054-3406
IS - 1
ER -