Likelihood Ratio Test of the Proportional Odds Assumption

Provides the means of testing the parallel regression assumption in the ordinal regression models. Also available is the brant.test().

LR.test(model, call=FALSE)

Arguments

model

a single model object to be tested.

call

a logical vector to indicate if the model call should be printed.

Value

model

the call of the model tested

df

the degrees of freedom

rdf

residual degrees of freedom

rdev

residual deviance

LRT

likelihood ratio test statistic

prob

the p-values of test

call

a logical vector

Details

The parallel regression assumption for the ordinal regression model can be tested With this function. It currently supports objects of class serp() and vglm().

See also

brant.test, hosmerlem, lipsitz, pulkroben

Examples

require(serp)
#> Loading required package: serp

sp <- serp(ordered(RET) ~ DIAB + GH + BP, link="logit",
           slope="parallel", reverse=TRUE, data = retinopathy)
LR.test(sp, call = TRUE)
#> 
#> Model:
#> serp(formula = ordered(RET) ~ DIAB + GH + BP, link = "logit", 
#>     slope = "parallel", reverse = TRUE, data = retinopathy)
#> 
#> LR-Test:
#>            rdf      rdev     LRT   df   pr(>chi)  
#> POM       1221    905.89                          
#> NPOM      1218    898.46   7.436    3    0.05923 .
#> ---
#> Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#> 
#> H0: Proportional odds assumption holds