Main Page | Directories | File List | Globals

ssclme.h File Reference

#include "sscCrosstab.h"
#include <R_ext/Lapack.h>
#include <R_ext/Constants.h>

Go to the source code of this file.

Functions

SEXP ssclme_create (SEXP facs, SEXP ncv)
SEXP ssclme_transfer_dimnames (SEXP x, SEXP facs, SEXP mmats)
SEXP ssclme_update_mm (SEXP x, SEXP facs, SEXP mmats)
SEXP ssclme_inflate_and_factor (SEXP x)
SEXP ssclme_factor (SEXP x)
SEXP ssclme_invert (SEXP x)
SEXP ssclme_initial (SEXP x)
SEXP ssclme_fixef (SEXP x)
SEXP ssclme_ranef (SEXP x)
SEXP ssclme_sigma (SEXP x, SEXP REML)
SEXP ssclme_coef (SEXP x, SEXP Unc)
SEXP ssclme_coefUnc (SEXP x)
SEXP ssclme_coefGetsUnc (SEXP x, SEXP coef)
SEXP ssclme_coefGets (SEXP x, SEXP coef, SEXP Unc)
SEXP ssclme_EMsteps (SEXP x, SEXP nsteps, SEXP REMLp, SEXP verb)
SEXP ssclme_fitted (SEXP x, SEXP facs, SEXP mmats, SEXP useRf)
SEXP ssclme_variances (SEXP x)
SEXP ssclme_grad (SEXP x, SEXP REMLp, SEXP Unc, SEXP OneVector)
SEXP ssclme_gradient (SEXP x, SEXP REMLp, SEXP Uncp)
SEXP ssclme_Hessian (SEXP x, SEXP REMLp, SEXP Uncp)
SEXP ssclme_collapse (SEXP x)
SEXP ssclme_to_lme (SEXP call, SEXP facs, SEXP x, SEXP model, SEXP REML, SEXP rep, SEXP fitted, SEXP residuals, SEXP terms, SEXP assign)


Function Documentation

SEXP ssclme_coef SEXP  x,
SEXP  Unconstr
 

Extract the upper triangles of the Omega matrices. These aren't "coefficients" but the extractor is called coef for historical reasons. Within each group these values are in the order of the diagonal entries first then the strict upper triangle in row order.

Parameters:
x pointer to an ssclme object
Unconstr pointer to a logical object indicating if the unconstrained parameterization should be used.
Returns:
numeric vector of the values in the upper triangles of the Omega matrices

SEXP ssclme_coefGets SEXP  x,
SEXP  coef,
SEXP  Unc
 

Assign the upper triangles of the Omega matrices. (Called coef for historical reasons.)

Parameters:
x pointer to an ssclme object
coef pointer to an numeric vector of appropriate length
Unc pointer to a logical object indicating if the unconstrained parameterization should be used.
Returns:
R_NilValue

SEXP ssclme_coefGetsUnc SEXP  x,
SEXP  coef
 

Assign the Omega matrices from the unconstrained parameterization.

Parameters:
x pointer to an ssclme object
coef pointer to an numeric vector of appropriate length
Returns:
R_NilValue

SEXP ssclme_coefUnc SEXP  x  ) 
 

Extract the unconstrained parameters that determine the Omega matrices. (Called coef for historical reasons.) The unconstrained parameters are derived from the LDL' decomposition of Omega_i. The first nc[i] entries in each group are the diagonals of log(D) followed by the strict lower triangle of L in column order.

Parameters:
x pointer to an ssclme object
Returns:
numeric vector of unconstrained parameters that determine the Omega matrices

SEXP ssclme_collapse SEXP  x  ) 
 

Copy an ssclme object collapsing the fixed effects slots to the response only.

Parameters:
x pointer to an ssclme object
Returns:
a duplicate of x with the fixed effects slots collapsed to the response only

SEXP ssclme_create SEXP  facs,
SEXP  ncv
 

Create an ssclme object from a list of grouping factors, sorted in order of non-increasing numbers of levels, and an integer vector of the number of columns in the model matrices. There is one more element in ncv than in facs. The last element is the number of columns in the model matrix for the fixed effects plus the response. (i.e. p+1)

Parameters:
facs pointer to a list of grouping factors
ncv pointer to an integer vector of number of columns per model matrix
Returns:
pointer to an ssclme object

SEXP ssclme_EMsteps SEXP  x,
SEXP  nsteps,
SEXP  REMLp,
SEXP  verb
 

Perform ECME steps for the REML or ML criterion.

Parameters:
x pointer to an ssclme object
nsteps pointer to an integer scalar - the number of ECME steps to perform
REMLp pointer to a logical scalar indicating if REML is to be used
verb pointer to a logical scalar indicating verbose mode
Returns:
NULL

SEXP ssclme_factor SEXP  x  ) 
 

If status[["factored"]] is FALSE, create and factor Z'Z+Omega, then create RZX and RXX, the deviance components, and the value of the deviance for both ML and REML.

Parameters:
x pointer to an ssclme object
Returns:
NULL

SEXP ssclme_fitted SEXP  x,
SEXP  facs,
SEXP  mmats,
SEXP  useRf
 

Calculate and return the fitted values.

Parameters:
x pointer to an ssclme object
facs list of grouping factors
mmats list of model matrices
useRf pointer to a logical scalar indicating if the random effects should be used
Returns:
pointer to a numeric array of fitted values

SEXP ssclme_fixef SEXP  x  ) 
 

Extract the conditional estimates of the fixed effects

Parameters:
x Pointer to an ssclme object
Returns:
a numeric vector containing the conditional estimates of the fixed effects

SEXP ssclme_grad SEXP  x,
SEXP  REMLp,
SEXP  Unc,
SEXP  OneVector
 

Return the gradient of the ML or REML deviance.

Parameters:
x pointer to an ssclme object
REMLp pointer to a logical scalar indicating if REML is to be used
Unc pointer to a logical scalar indicating if the unconstrained parameterization is to be used
OneVector pointer to a logical scalar indicating if result should be a single vector.
Returns:
pointer to the gradient as a list of matrices or as a vector.

SEXP ssclme_gradient SEXP  x,
SEXP  REMLp,
SEXP  Uncp
 

SEXP ssclme_Hessian SEXP  x,
SEXP  REMLp,
SEXP  Uncp
 

Return the Hessian of the ML or REML deviance. This is a placeholder until I work out the evaluation of the analytic Hessian, which probably will involve several helper functions.

Parameters:
x pointer to an ssclme object
REMLp pointer to a logical scalar indicating if REML is to be used
Uncp pointer to a logical scalar indicating if the unconstrained parameterization is to be used
Returns:
pointer to an approximate Hessian matrix

SEXP ssclme_inflate_and_factor SEXP  x  ) 
 

Inflate Z'Z according to Omega and create the factorization LDL'

Parameters:
x pointer to an ssclme object
Returns:
NULL

SEXP ssclme_initial SEXP  x  ) 
 

Create and insert initial values for Omega_i.

Parameters:
x pointer to an ssclme object
Returns:
NULL

SEXP ssclme_invert SEXP  x  ) 
 

If necessary, factor Z'Z+Omega, ZtX, and XtX then, if necessary, form RZX, RXX, and bVar for the inverse of the Cholesky factor.

Parameters:
x pointer to an ssclme object
Returns:
NULL (x is updated in place)

SEXP ssclme_ranef SEXP  x  ) 
 

Extract the conditional modes of the random effects.

Parameters:
x Pointer to an ssclme object
Returns:
a list containing the conditional modes of the random effects

SEXP ssclme_sigma SEXP  x,
SEXP  REML
 

Extract the ML or REML conditional estimate of sigma

Parameters:
x pointer to an ssclme object
REML logical scalar - TRUE if REML estimates are requested
Returns:
numeric scalar

SEXP ssclme_to_lme SEXP  call,
SEXP  facs,
SEXP  x,
SEXP  model,
SEXP  REML,
SEXP  rep,
SEXP  fitted,
SEXP  residuals,
SEXP  terms,
SEXP  assign
 

Create an lme object from its components. This is not done by new("lme", ...) at the R level because of the possibility of causing the copying of very large objects.

Parameters:
call Pointer to the original call
facs pointer to the list of grouping factors
x pointer to the model matrices (may be of length zero)
model pointer to the model frame
REML pointer to a logical scalar indicating if REML is used
rep pointer to the converged ssclme object
fitted pointer to the fitted values
residuals pointer to the residuals
terms pointer to a terms object (redundant if model is non-empty)
assign pointer to an integer assign vector
Returns:
an lme object

SEXP ssclme_transfer_dimnames SEXP  x,
SEXP  facs,
SEXP  mmats
 

Copy the dimnames from the list of grouping factors and the model matrices for the grouping factors into the appropriate parts of the ssclme object.

Parameters:
x pointer to an ssclme object
facs pointer to a list of factors
mmats pointer to a list of model matrices
Returns:
NULL

SEXP ssclme_update_mm SEXP  x,
SEXP  facs,
SEXP  mmats
 

Update the numerical entries x, ZtX, and XtX in an ssclme object according to a set of model matrices.

Parameters:
x pointer to an ssclme object
facs pointer to a list of grouping factors
mmats pointer to a list of model matrices
Returns:
NULL

SEXP ssclme_variances SEXP  x  ) 
 

Return the unscaled variances

Parameters:
x pointer to an ssclme object
Returns:
a list similar to the Omega list with the unscaled variances


Generated on Wed Mar 30 08:43:58 2005 for Matrix by  doxygen 1.4.1