Stratified bivariate robust local regression
This function performs robust local regression of a variable z
on predictor variables x
and y
, separately within values of a fourth variable g
. It is used by maNorm2D
for 2D spatial location normalization.
ma2D(x, y, z, g, w=NULL, subset=TRUE, span=0.4, ...)
x |
A numeric vector of predictor variables. |
y |
A numeric vector of predictor variables. |
z |
A numeric vector of responses. |
g |
Variables used to stratify the data. |
w |
An optional numeric vector of weights. |
subset |
A "logical" or "numeric" vector indicating the subset of points used to compute the fits. |
span |
The argument |
... |
Misc arguments |
z
is regressed on x
and y
, separately within values of g
using the loess
function.
A numeric vector of fitted values.
Sandrine Dudoit, http://www.stat.berkeley.edu/~sandrine.
S. Dudoit and Y. H. Yang. (2002). Bioconductor R packages for exploratory analysis and normalization of cDNA microarray data. In G. Parmigiani, E. S. Garrett, R. A. Irizarry and S. L. Zeger, editors, The Analysis of Gene Expression Data: Methods and Software, Springer, New York.
# See examples for maNormMain.
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.