HGPREDICT procedure
Forms predictions from a hierarchical or double hierarchical generalized linear model
analysis (R.W. Payne, Y. Lee, J.A. Nelder & M. Noh).
Options
PRINT = string
What to print (description, predictions, se, sed,
vcovariance); default desc, pred, se
COMBINATIONS = string
Which combinations of factors in the current model
to include (full, present, estimable); default esti
ADJUSTMENT = string
Type of adjustment (marginal, equal); default
marg
WEIGHTS = table
Weights classified by some or all of the factors in the
model; default *
OFFSET = scalar
Value of offset on which to base predictions; default mean
of offset variate
METHOD = string
Method of forming margin (mean, total); default mean
ALIASING = string
How to deal with aliased parameters (fault, ignore);
default faul
BACKTRANSFORM = string
What back-transformation to apply to the values on
the linear scale, before calculating the predicted means (link, none); default none
NOMESSAGE = strings
Which warning messages to suppress (dispersion,
nonlinear); default *
NBINOMIAL = scalar
Supplies the total number of trials to be used for
prediction with a binomial distribution (providing a value n greater than one allows
predictions to be made of the number of "successes" out of n, whereas the value 1
predicts the proportion of successes); default 1
PREDICTIONS = table or scalar
To save the predictions; default *
SE = table or scalar
To save standard errors of predictions; default *
SED = symmetric matrix
To save matrices of standard errors of differences
between predictions; default *
VCOVARIANCE = symmetric matrix
To save variance-covariance matrices of
predictions; default *
SAVE = pointer
Specifies the save structure (from
HGANALYSE) of
the analysis from which to predict; default uses the most recent analysis
Parameters
CLASSIFY = vectors
Variates and/or factors to classify table of predictions
LEVELS = variates or scalars
To specify values of variates, levels of factors
Description
HGPREDICT is one of several procedures with the prefix HG, which provide tools for fitting
the hierarchical and double hierarchical generalized linear models (HGLMs and DHGLMs)
defined by Lee & Nelder (1996, 2001, 2006). The models are defined by the
HGFIXEDMODEL, HGRANDOMMODEL and
HGDRANDOMMODEL procedures, and fitted by the HGANALYSE
procedure. HGPREDICT allows you to form predictions for various values of the fixed
parameters. The predictions are at mean values of the random distributions (i.e. taking
zero contributions from the random effects to the linear predictor).
HGPREDICT uses the PREDICT directive internally. Its options and
parameters are a subset of those of PREDICT, and are used in the same way
except that back-transformations are possible only with conjugate models. Consequently,
the default for option BACKTRANSFORM is none.
Options: PRINT, COMBINATIONS, ADJUSTMENT, WEIGHTS, OFFSET, METHOD, ALIASING,
BACKTRANSFORM, NOMESSAGE, NBINOMIAL, PREDICTIONS, SE, SED, VCOVARIANCE, SAVE.
Parameters: CLASSIFY, LEVELS.
Method
HGPREDICT forms the predictions using the PREDICT directive.
References
Lee, Y., & Nelder, J.A. (1996). Hierarchical generalized linear models (with discussion).
Journal of the Royal Statistical Society, Series B, 58, 619-678.
Lee, Y., & Nelder, J.A. (2001). Hierarchical generalized linear models: a synthesis of
generalised linear models, random-effect models and structured dispersions. Biometrika,
88, 987-1006.
Lee, Y. & Nelder, J.A. (2006). Double hierarchical generalized linear models (with
discussion). Appl. Statist., 55, 139-185.