Object
~~|
~~+--ParametersInterface
~~~~~~~|
~~~~~~~+--Model
~~~~~~~~~~~~|
~~~~~~~~~~~~+--UnitModel
~~~~~~~~~~~~~~~~~|
~~~~~~~~~~~~~~~~~+--MultiArrayUnitModel
~~~~~~~~~~~~~~~~~~~~~~|
~~~~~~~~~~~~~~~~~~~~~~+--ProbeLevelModel
~~~~~~~~~~~~~~~~~~~~~~~~~~~|
~~~~~~~~~~~~~~~~~~~~~~~~~~~+--AffinePlm
Directly known subclasses:
AffineCnPlm, AffineSnpPlm
public abstract static class AffinePlm
extends ProbeLevelModel
This class represents affine model in Bengtsson & Hossjer (2006).AffinePlm(..., background=TRUE)ProbeLevelModel.getProbeAffinityFile -
}Methods inherited from ProbeLevelModel: calculateResidualSet, calculateWeights, fit, getAsteriskTags, getCalculateResidualsFunction, getChipEffectSet, getProbeAffinityFile, getResidualSet, getRootPath, getWeightsSet
Methods inherited from MultiArrayUnitModel: getListOfPriors, setListOfPriors, validate
Methods inherited from UnitModel: findUnitsTodo, getAsteriskTags, getFitSingleCellUnitFunction, getParameters
Methods inherited from Model: as.character, fit, getAlias, getAsteriskTags, getDataSet, getFullName, getName, getPath, getRootPath, getTags, setAlias, setTags
Methods inherited from ParametersInterface: getParameterSets, getParameters, getParametersAsString
Methods inherited from Object: $, $<-, [[, [[<-, as.character, attach, attachLocally, clearCache, clearLookupCache, clone, detach, equals, extend, finalize, getEnvironment, getFieldModifier, getFieldModifiers, getFields, getInstantiationTime, getStaticInstance, hasField, hashCode, ll, load, objectSize, print, save, asThis
$$y_{ik} = a + \theta_i \phi_k + \varepsilon_{ik}$$
where $a$ is an offset common to all probe signals, $\theta_i$ are the chip effects for arrays $i=1,...,I$, and $\phi_k$ are the probe affinities for probes $k=1,...,K$. The $\varepsilon_{ik}$ are zero-mean noise with equal variance. The model is constrained such that $\prod_k \phi_k = 1$.
Note that with the additional constraint $a=0$ (see arguments above),
the above model is very similar to MbeiPlm. The differences in
parameter estimates is due to difference is assumptions about the
error structure, which in turn affects how the model is estimated.