clm: Cumulative Link Models

Description

Fits cumulative link models (CLMs) such as the propotional odds model. The model allows for various link functions and structured thresholds that restricts the thresholds or cut-points to be e.g., equidistant or symmetrically arranged around the central threshold(s). Nominal effects (partial proportional odds with the logit link) are also allowed. A modified Newton algorithm is used to optimize the likelihood function.

Usage

clm(formula, scale, nominal, data, weights, start, subset, doFit = TRUE,
  na.action, contrasts, model = TRUE, control=list(),
  link = c("logit", "probit", "cloglog", "loglog", "cauchit", 
           "Aranda-Ordaz", "log-gamma"),
  threshold = c("flexible", "symmetric", "symmetric2", "equidistant"), ...)

Value

If doFit = FALSE the result is an environment representing the model ready to be optimized. If doFit = TRUE the result is an object of class "clm" with the components listed below.

Note that some components are only present if scale and

nominal are used.

aliased: list of length 3 or less with components alpha, beta and zeta each being logical vectors containing alias information for the parameters of the same names.
alpha: a vector of threshold parameters.
alpha.mat: (where relevant) a table (data.frame) of threshold parameters where each row corresponds to an effect in the nominal formula.
beta: (where relevant) a vector of regression parameters.
call: the mathed call.
coefficients: a vector of coefficients of the form c(alpha, beta, zeta)
cond.H: condition number of the Hessian matrix at the optimum (i.e. the ratio of the largest to the smallest eigenvalue).
contrasts: (where relevant) the contrasts used for the formula part of the model.
control: list of control parameters as generated by clm.control.
convergence: convergence code where 0 indicates successful convergence and negative values indicate convergence failure; 1 indicates successful convergence to a non-unique optimum.
edf: the estimated degrees of freedom, i.e., the number of parameters in the model fit.
fitted.values: the fitted probabilities.
gradient: a vector of gradients for the coefficients at the estimated optimum.
Hessian: the Hessian matrix for the parameters at the estimated optimum.
info: a table of basic model information for printing.
link: character, the link function used.
logLik: the value of the log-likelihood at the estimated optimum.
maxGradient: the maximum absolute gradient, i.e., max(abs(gradient)).
model: if requested (the default), the model.frame containing variables from formula, scale and nominal parts.
n: the number of observations counted as nrow(X), where X is the design matrix.
na.action: (where relevant) information returned by model.frame on the special handling of NAs.
nobs: the number of observations counted as sum(weights).
nom.contrasts: (where relevant) the contrasts used for the nominal part of the model.
nom.terms: (where relevant) the terms object for the nominal part.
nom.xlevels: (where relevant) a record of the levels of the factors used in fitting for the nominal part.
start: the parameter values at which the optimization has started. An attribute start.iter gives the number of iterations to obtain starting values for models where scale is specified or where the cauchit link is chosen.
S.contrasts: (where relevant) the contrasts used for the scale part of the model.
S.terms: (where relevant) the terms object for the scale part.
S.xlevels: (where relevant) a record of the levels of the factors used in fitting for the scale part.
terms: the terms object for the formula part.
Theta: (where relevant) a table (data.frame) of thresholds for all combinations of levels of factors in the nominal formula.
threshold: character, the threshold structure used.
tJac: the transpose of the Jacobian for the threshold structure.
xlevels: (where relevant) a record of the levels of the factors used in fitting for the formula part.
y.levels: the levels of the response variable after removing levels for which all weights are zero.
zeta: (where relevant) a vector of scale regression parameters.

Arguments

formula: a formula expression as for regression models, of the form response ~ predictors. The response should be a factor (preferably an ordered factor), which will be interpreted as an ordinal response with levels ordered as in the factor. The model must have an intercept: attempts to remove one will lead to a warning and will be ignored. An offset may be used. See the documentation of formula for other details.
scale: an optional formula expression, of the form ~ predictors, i.e. with an empty left hand side. An offset may be used. Variables included here will have multiplicative effects and can be interpreted as effects on the scale (or dispersion) of a latent distribution.
nominal: an optional formula of the form ~ predictors, i.e. with an empty left hand side. The effects of the predictors in this formula are assumed to be nominal rather than ordinal - this corresponds to the so-called partial proportional odds (with the logit link).
data: an optional data frame in which to interpret the variables occurring in the formulas.
weights: optional case weights in fitting. Defaults to 1. Negative weights are not allowed.
start: initial values for the parameters in the format c(alpha, beta, zeta), where alpha are the threshold parameters (adjusted for potential nominal effects), beta are the regression parameters and zeta are the scale parameters.
subset: expression saying which subset of the rows of the data should be used in the fit. All observations are included by default.
doFit: logical for whether the model should be fitted or the model environment should be returned.
na.action: a function to filter missing data. Applies to terms in all three formulae.
contrasts: a list of contrasts to be used for some or all of the factors appearing as variables in the model formula.
model: logical for whether the model frame should be part of the returned object.
control: a list of control parameters passed on to clm.control.
link: link function, i.e., the type of location-scale distribution assumed for the latent distribution. The default "logit" link gives the proportional odds model.
threshold: specifies a potential structure for the thresholds (cut-points). "flexible" provides the standard unstructured thresholds, "symmetric" restricts the distance between the thresholds to be symmetric around the central one or two thresholds for odd or equal numbers or thresholds respectively, "symmetric2" restricts the latent mean in the reference group to zero; this means that the central threshold (even no. response levels) is zero or that the two central thresholds are equal apart from their sign (uneven no. response levels), and "equidistant" restricts the distance between consecutive thresholds to be of the same size.
...: additional arguments are passed on to clm.control.

Author

Rune Haubo B Christensen

Details

This is a new (as of August 2011) improved implementation of CLMs. The old implementation is available in clm2, but will probably be removed at some point.

There are methods for the standard model-fitting functions, including summary, anova, model.frame, model.matrix, drop1, dropterm, step, stepAIC, extractAIC, AIC, coef, nobs, profile, confint, vcov and slice.

Examples

Run this code


fm1 <- clm(rating ~ temp * contact, data = wine)
fm1 ## print method
summary(fm1)
fm2 <- update(fm1, ~.-temp:contact)
anova(fm1, fm2)

drop1(fm1, test = "Chi")
add1(fm1, ~.+judge, test = "Chi")

fm2 <- step(fm1)
summary(fm2)

coef(fm1)
vcov(fm1)
AIC(fm1)
extractAIC(fm1)
logLik(fm1)
fitted(fm1)

confint(fm1) ## type = "profile"
confint(fm1, type = "Wald")
pr1 <- profile(fm1)
confint(pr1)

## plotting the profiles:
par(mfrow = c(2, 2))
plot(pr1, root = TRUE) ## check for linearity
par(mfrow = c(2, 2))
plot(pr1)
par(mfrow = c(2, 2))
plot(pr1, approx = TRUE)
par(mfrow = c(2, 2))
plot(pr1, Log = TRUE)
par(mfrow = c(2, 2))
plot(pr1, Log = TRUE, relative = FALSE)

## other link functions:
fm4.lgt <- update(fm1, link = "logit") ## default
fm4.prt <- update(fm1, link = "probit")
fm4.ll <- update(fm1, link = "loglog")
fm4.cll <- update(fm1, link = "cloglog")
fm4.cct <- update(fm1, link = "cauchit")
anova(fm4.lgt, fm4.prt, fm4.ll, fm4.cll, fm4.cct)

## structured thresholds:
fm5 <- update(fm1, threshold = "symmetric")
fm6 <- update(fm1, threshold = "equidistant")
anova(fm1, fm5, fm6)

## the slice methods:
slice.fm1 <- slice(fm1)
par(mfrow = c(3, 3))
plot(slice.fm1)
## see more at '?slice.clm'

## Another example:
fm.soup <- clm(SURENESS ~ PRODID, data = soup)
summary(fm.soup)

if(require(MASS)) { ## dropterm, addterm, stepAIC, housing
    fm1 <- clm(rating ~ temp * contact, data = wine)
    dropterm(fm1, test = "Chi")
    addterm(fm1, ~.+judge, test = "Chi")
    fm3 <- stepAIC(fm1)
    summary(fm3)

    ## Example from MASS::polr:
    fm1 <- clm(Sat ~ Infl + Type + Cont, weights = Freq, data = housing)
    summary(fm1)
}

Run the code above in your browser using DataLab