anova.ocm: Anova method for Continuous Ordinal Fits

In ordinalCont: Ordinal Regression Analysis for Continuous Scales

Description

Comparison of continuous ordinal models using likelihood ratio tests.

Usage

## S3 method for class 'ocm'
anova(object, ...)

Arguments

object	an object of class ocm
...	one or more additional ocm objects

Details

Likelihood ratio testing of nested models is performed.

Value

The method returns an object of class anova.ocm and data.frame, reporting for each model, in hierarchical order:

no.par	number of parameters
AIC	Akaike information criterion
loglik	log-likelihood
LR.stat	likelihood ratio statistic
df	difference in the degrees of freedom in the models being compared
Pr(>Chisq)	p-value from the likelihood ratio test

Author(s)

Maurizio Manuguerra, Gillian Heller @seealso ocm, print.anova.ocm

Examples

## Not run: 
fit.overall  <- ocm(overall  ~ cycleno + bsa + treatment, data=ANZ0001.sub, scale=c(0,100))
anova(fit.overall, update(fit.overall, .~. + age))

## End(Not run)

Example output

Loading required package: boot
Loading required package: splines
Ext.iters	Int.iters	lambda		Convergence (<0.01)
1 		 122 		 3.624415e-05 		 1 		 
2 		 68 		 0.0001081574 		 1.9841 		 
3 		 28 		 0.0002661319 		 1.4606 		 
4 		 20 		 0.0004563513 		 0.7148 		 
5 		 21 		 0.000615229 		 0.3481 		 
6 		 18 		 0.0007260145 		 0.1801 		 
7 		 13 		 0.0007956493 		 0.0959 		 
8 		 9 		 0.0008370342 		 0.052 		 
9 		 6 		 0.0008607871 		 0.0284 		 
10 		 4 		 0.0008744701 		 0.0159 		 
11 		 3 		 0.0008831887 		 0.01 		 
Ext.iters	Int.iters	lambda		Convergence (<0.01)
1 		 122 		 3.622746e-05 		 1 		 
2 		 68 		 0.0001080966 		 1.9838 		 
3 		 28 		 0.0002660217 		 1.461 		 
4 		 20 		 0.0004562487 		 0.7151 		 
5 		 21 		 0.0006151645 		 0.3483 		 
6 		 18 		 0.0007259948 		 0.1802 		 
7 		 13 		 0.0007956677 		 0.096 		 
8 		 9 		 0.0008370805 		 0.052 		 
9 		 6 		 0.000860852 		 0.0284 		 
10 		 4 		 0.0008745468 		 0.0159 		 
11 		 3 		 0.0008832735 		 0.01 		 
16.94854 17.94776 
1 2 
[Penalized] likelihood ratio tests of ordinal regression models for continuous scales:
 
         formula                                   link 
Model 1: overall ~ cycleno + bsa + treatment       logit
Model 2: overall ~ cycleno + bsa + treatment + age logit

            edf     AIC penlogLik LR.stat      df Pr(>Chisq)
Model 1: 16.949 -44.885    33.476                           
Model 2: 17.948 -42.896    33.481  0.0095 0.99922      0.922

ordinalCont documentation built on Dec. 3, 2020, 1:06 a.m.