algorithms.statistics.nlsmodel

Module: algorithms.statistics.nlsmodel

Inheritance diagram for nipy.algorithms.statistics.nlsmodel:

TODO

NLSModel

class nipy.algorithms.statistics.nlsmodel.NLSModel(Y, design, f, grad, theta, niter=10)

Bases: nipy.fixes.scipy.stats.models.model.Model

Class representing a simple nonlinear least squares model.

Methods

SSE
fit
getZ
getomega
initialize
next
predict

__init__(Y, design, f, grad, theta, niter=10)

Parameters :

Y : TODO

the data in the NLS model

design : TODO

the deisng matrix, X

f : TODO

the map between the linear parameters (in the design matrix) and the nonlinear parameters (theta)

grad : TODO

the gradient of f, this should be a function of an nxp design matrix X and qx1 vector theta that returns an nxq matrix df_i/dtheta_j where

f_i(theta) = f(X[i], theta)

is the nonlinear response function for the i-th instance in the model.

SSE()

Sum of squares error.

:Returns; TODO

fit()

Fit a model to data.

getZ()

Returns :None

getomega()

Returns :None

initialize()

Initialize (possibly re-initialize) a Model instance. For instance, the design matrix of a linear model may change and some things must be recomputed.

next()

Returns :None

predict(design=None)

Parameters :

design : TODO

TODO

Returns :

TODO