gnlm (version 1.1.1)

ordglm: Generalized Linear Ordinal Regression Models

Description

ordglm fits linear regression functions with logistic or probit link to ordinal response data by proportional odds.

Usage

ordglm(formula, data = parent.frame(), link = "logit", maxiter = 10,
  weights = 1)

Arguments

formula

A model formula. The response must be integers numbered from zero to one less than the number of ordered categories.

data

An optional data frame containing the variables in the model.

link

Logit or probit link function.

maxiter

Maximum number of iterations allowed.

weights

A vector containing the frequencies for grouped data.

Value

A list of class ordglm is returned. The printed output includes the -log likelihood, the corresponding AIC, the deviance, the maximum likelihood estimates, standard errors, and correlations.

References

Jansen, J. (1991) Fitting regression models to ordinal data. Biometrical Journal 33, 807-815.

Johnson, V.E. and Albert, J.H. (1999) Ordinal Data Modeling. Springer-Verlag.

See Also

glm, nordr

Examples

# NOT RUN {
# McCullagh (1980) JRSS B42, 109-142
# tonsil size: 2x3 contingency table
y <- c(0:2,0:2)
carrier <- gl(2,3,6)
wt <- c(19,29,24,497,560,269)
ordglm(y~carrier, weights=wt)

# }