RSModel.fit: Rating Scale Model Fitting Function

Description

RSModel.fit is a basic fitting function for rating scale models.

Usage

RSModel.fit(y, weights = NULL, start = NULL, reltol = 1e-10,
  deriv = c("sum", "diff"), hessian = TRUE,
  maxit = 100L, full = TRUE, ...)

Arguments

object that can be coerced (via as.matrix). Typically either already a matrix or a data.frame

weights

an optional vector of weights, interpreted as case
    weights (integer only).

deriv

character. If "sum" (the default), the first derivatives
    of the elementary symmetric functions are calculated with the sum
    algorithm. Otherwise ("diff") the difference algorithm (faster but
    numerically unstable) is used.

start

an optional vector of starting values.

hessian

logical. Should the Hessian of the final model be computed?
    If set to FALSE, the vcov method can only return NAs
    and consequently no standard errors or tests are available in the
    summary.

reltol, maxit, ...

further arguments passed to optim.

full

logical. Should a full model object be returned? If set to FALSE,
    no variance-covariance matrix and no matrix of estimating functions are computed.

`Value`

RSModel.fit returns an S3 object of class "RSModel", 
  i.e., a list with components as follows.
coefficientsa named vector of estimated item difficulty
    parameters (without first item parameter which is constrained
    to 0) and estimated treshold parameters (again without first
    threshold parameter which is also constrained to 0),
vcovcovariance matrix of the parameters in the model,
datamodified data, used for model-fitting, i.e., cleaned for items without
    variance, centralized so that the first category is zero for all items
    and without observations with zero weight. Be careful, this is different than for
    objects of class "RaschModel" or "btReg", where
    data contains the original data,
itemslogical vector of length ncol(y), which
    indicates which items have variance (TRUE), i.e., are identified and have been
    used for the estimation or not (FALSE),
categoriesinteger vector of length ncol(y), which
    contains the number of categories minus one per item,
nnumber of observations (with non-zero weights),
n_orgoriginal number of observations in y,
weightsthe weights used (if any),
nalogical indicating whether the data contains NAs,
esflist of elementary symmetric functions and their
    derivatives for estimated parameters,
logliklog-likelihood of the fitted model,
dfnumber of estimated parameters,
codeconvergence code from optim,
iterationsnumber of iterations used by optim,
reltoltolerance passed to optim.

`Details`

RSModel.fit provides a basic fitting function for rating scales models,
  intended as a building block for fitting rating scale trees.
  
  RSModel.fit returns an object of class "RSModel" (and
  class "PCModel") for which several basic methods
  are available, including print, plot,
  summary, coef, vcov, and logLik.

`See Also`

PCModel.fit, RaschModel.fit, btReg.fit

`Examples`

Run this code## Verbal aggression data
data("VerbalAggression", package = "psychotools")

## Rating scale model for the other-to-blame situations
rsm <- RSModel.fit(VerbalAggression$resp[, 1:12])
summary(rsm)
plot(rsm)
Run the code above in your browser using DataLab