eh {CoCoRaw} | R Documentation |
After using the "Fast Procedure for Model Search", the EH-procedure, by Edwards and Havranek (1985, 1985) any model can be labeled as accepted or as rejected. By the principles of weak acceptance, weak rejection, and coherence, the search space of all hierarchical graphical, or decomposable models is divided into two sets of models: The class of minimal acceptable models, and the class of maximal rejected models.
eh(strategy = c("smallest", "alternating", "rough")[1], sub.class = c("decomposable", "graphical", "hierarchical")[2], p.accepted = FALSE, data = NULL, object = .object.of.thing(data = data, ...), ...)
strategy |
A character string.
The argument strategy should be
"smallest" ,
"alternating" ,
or "rough" .
See the section "Details" below.
|
sub.class |
A character string.
The argument sub.class should be
"decomposable" ,
"graphical" ,
or "hierarchical" .
See the section "Details" below.
|
p.accepted |
Numeric, models with p-value greater than
p.accepted are accepted, else they are rejected. |
data |
See exportCoCo . |
object |
See exportCoCo . |
... |
Additional arguments to generate the CoCo object
from the data argument. See propertyModel . |
TRUE
Jens Henrik Badsberg
Badsberg, J.H. (2001): A guide to CoCo, JSS ( http://www.jstatsoft.org/v06/i04/ ).
Badsberg, J.H. (1996): Xlisp+CoCo, Aalborg University.
Edwards, D. and Havranek, T. (1985). A fast procedure for model search in multidimensional contingency tables. Biometrika 72: 339-351.
Edwards, D. and Havranek, T. (1987). A fast model selection procedure for large families of models. J. Amer. Stat. Assoc. 82: 205-231.
forward
, backward
,
and disposeOfEh
.
library(CoCo); data(Reinis); CoCoObject <- makeCoCo(); enterTable(Reinis, object = CoCoObject); eh(sub.class = "decomposable", object = CoCoObject); eh(sub.class = "graphical", object = CoCoObject); eh(sub.class = "hierarchical", object = CoCoObject); endCoCo(object = CoCoObject);