TukeyBiweight {DescTools} | R Documentation |
This calculates a robust average that is unaffected by outliers.
TukeyBiweight(x, const = 9, na.rm = FALSE,
conf.level = NA, ci.type = "bca", R=1000, ...)
x |
a |
const |
a constant. |
na.rm |
logical, indicating whether |
conf.level |
confidence level of the interval. If set to |
ci.type |
The type of confidence interval required. The value should be any subset
of the values |
R |
The number of bootstrap replicates. Usually this will be a single positive integer. For importance resampling,
some resamples may use one set of weights and others use a different set of weights. In this case |
... |
the dots are passed to the function |
This is a one step computation that follows the Affy whitepaper below,
see page 22. const
determines the point at which
outliers are given a weight of 0 and therefore do not contribute to
the calculation of the mean. const = 9
sets values roughly
+/-6 standard deviations to 0. const = 6
is also used in
tree-ring chronology development. Cook and Kairiukstis (1990) have
further details.
An exact summation algorithm (Shewchuk 1997) is used. When some assumptions about the rounding of floating point numbers and conservative compiler optimizations hold, summation error is completely avoided. Whether the assumptions hold depends on the platform, i.e. compiler and CPU.
A numeric
mean.
Mikko Korpela <mikko.korpela@aalto.fi>
Statistical Algorithms Description Document, 2002, Affymetrix.
Cook, E. R. and Kairiukstis, L. A. (1990) Methods of Dendrochronology: Applications in the Environmental Sciences. Springer. ISBN-13: 978-0792305866.
Mosteller, F. and Tukey, J. W. (1977) Data Analysis and Regression: a second course in statistics. Addison-Wesley. ISBN-13: 978-0201048544.
Shewchuk, J. R. (1997) Adaptive Precision Floating-Point Arithmetic and Fast Robust Geometric Predicates. Discrete and Computational Geometry, 18(3):305-363. Springer.
TukeyBiweight(rnorm(100))