Chapter Contents |
Previous |
Next |
The NLMIXED Procedure |
Option | Description |
Basic Options | |
DATA= | input data set |
METHOD= | integration method |
Displayed Output Specifications | |
START | gradient at starting values |
HESS | Hessian matrix |
ITDETAILS | iteration details |
CORR | correlation matrix |
COV | covariance matrix |
ECORR | corr matrix of additional estimates |
ECOV | cov matrix of additional estimates |
EDER | derivatives of additional estimates |
ALPHA= | alpha for confidence limits |
DF= | degrees of freedom for p values and confidence limits |
Debugging Output | |
LIST | model program, variables |
LISTCODE | compiled model program |
LISTDEP | model dependency listing |
LISTDER | model derivative |
XREF | model cross reference |
FLOW | model execution messages |
TRACE | detailed model execution messages |
Quadrature Options | |
NOAD | no adaptive centering |
NOADSCALE | no adaptive scaling |
OUTQ= | output data set |
QFAC= | search factor |
QMAX= | maximum points |
QPOINTS= | number of points |
QSCALEFAC= | scale factor |
QTOL= | tolerance |
Empirical Bayes Options | |
EBSTEPS= | number of Newton steps |
EBSUBSTEPS= | number of substeps |
EBSSFRAC= | step-shortening fraction |
EBSSTOL= | step-shortening tolerance |
EBTOL= | convergence tolerance |
EBOPT | comprehensive optimization |
EBZSTART | zero starting values |
Optimization Specifications | |
TECHNIQUE= | minimization technique |
UPDATE= | update technique |
LINESEARCH= | line-search method |
LSPRECISION= | line-search precision |
HESCAL= | type of Hessian scaling |
INHESSIAN= | start for approximated Hessian |
RESTART= | iteration number for update restart |
OPTCHECK[=] | check optimality in neighborhood |
Derivatives Specifications | |
FD[=] | finite-difference derivatives |
FDHESSIAN[=] | finite-difference second derivatives |
DIAHES | use only diagonal of Hessian |
Constraint Specifications | |
LCEPSILON= | range for active constraints |
LCDEACT= | LM tolerance for deactivating |
LCSINGULAR= | tolerance for dependent constraints |
Termination Criteria Specifications | |
MAXFUNC= | maximum number of function calls |
MAXITER= | maximum number of iterations |
MINITER= | minimum number of iterations |
MAXTIME= | upper limit seconds of CPU time |
ABSCONV= | absolute function convergence criterion |
ABSFCONV= | absolute function convergence criterion |
ABSGCONV= | absolute gradient convergence criterion |
ABSXCONV= | absolute parameter convergence criterion |
FCONV= | relative function convergence criterion |
FCONV2= | relative function convergence criterion |
GCONV= | relative gradient convergence criterion |
XCONV= | relative parameter convergence criterion |
FDIGITS= | number accurate digits in objective function |
FSIZE= | used in FCONV, GCONV criterion |
XSIZE= | used in XCONV criterion |
Step Length Specifications | |
DAMPSTEP[=] | damped steps in line search |
MAXSTEP= | maximum trust-region radius |
INSTEP= | initial trust-region radius |
Singularity Tolerances | |
SINGCHOL= | tolerance for Cholesky roots |
SINGHESS= | tolerance for Hessian |
SINGSWEEP= | tolerance for sweep |
SINGVAR= | tolerance for variances |
Covariance Matrix Tolerances | |
ASINGULAR= | absolute singularity for inertia |
MSINGULAR= | relative M singularity for inertia |
VSINGULAR= | relative V singularity for inertia |
G4= | threshold for Moore-Penrose inverse |
COVSING= | tolerance for singular COV matrix |
CFACTOR= | multiplication factor for COV matrix |
TECH= | UPDATE= | LSP default |
QUANEW | DBFGS, BFGS | r = 0.4 |
QUANEW | DDFP, DFP | r = 0.06 |
CONGRA | all | r = 0.1 |
NEWRAP | no update | r = 0.9 |
Chapter Contents |
Previous |
Next |
Top |
Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.