ssym (version 1.5.1)

ssym.l: Fitting Semi-parametric Symmetric Regression Models

Description

ssym.l is used to fit a semi-parametric regression model suitable for data set analysis in which the conditional distribution of the response is symmetric and continuous. In this setup, both location and dispersion parameters of the response variable distribution are explicitly modeled through semi-parametric functions, which may be approximated by natural cubic splines or P-splines.

Usage

ssym.l(formula, family, xi, data, epsilon, maxiter, subset, local.influence)

Arguments

formula

a symbolic description of the systematic component of the model to be fitted. See details for further information.

family

a description of the error distribution to be used in the model. Supported families include Normal, Student, Contnormal, Powerexp, Hyperbolic, Slash, Sinh-normal and Sinh-t

xi

a numeric value or numeric vector that represents the extra parameter of the specified error distribution.

data

an optional data frame, list or environment containing the variables in the model.

epsilon

an optional positive value, which represents the convergence criterion. Default value is 1e-07.

maxiter

an optional positive integer giving the maximal number of iterations for the estimating process. Default value is 1e03.

subset

an optional expression specifying a subset of individuals to be used in the fitting process.

local.influence

logical. If TRUE, local influence measures under two perturbation schemes are calculated.

Value

• coefs.mu
  a vector of parameter estimates associated with the nonlinear function fitted to the location of the response (or log-response) variable.
• coefs.phi
  a vector of parameter estimates associated with the semiparametric function fitted to the dispersion of the response (or log-response) variable.
• se.mu
  approximated standard errors asociated with coefs.mu.
• se.phi
  approximated standard errors asociated with coefs.phi.
• weights
  final weights of the iterative process.
• lambda.mu
  estimate for the smoothing parameter associated to the location parameter.
• dfe.mu
  degrees of freedom associated with the nonparametric part of the location submodel.
• lambda.phi
  estimate for the smoothing parameter associated to the dispersion parameter.
• dfe.phi
  degrees of freedom associated with the nonparametric part of the dispersion submodel.
• deviance.mu
  a vector of deviances associated with the location of the response (or log-response) variable.
• deviance.phi
  a vector of deviances associated with the dispersion of the response (or log-response) variable.
• mu.fitted
  a vector of fitted values for the location of the response (or log-response) variable.
• phi.fitted
  a vector of fitted values for the dispersion of the response (or log-response) variable.
• lpdf
  a vector of individual contributions to the log-likelihood function.
• cdfz
  a vector of the cumulative distribution function of each individual.
• cw
  if local.influence=TRUE, a matrix of local influence and total local influence measures (under the case-weight perturbation scheme) associated with coefs.mu and based on the conformal normal curvature.
• pr
  if local.influence=TRUE, a matrix of local influence and total local influence measures (under the response perturbation scheme) associated with coefs.mu and based on the conformal normal curvature.
• cw.theta
  if local.influence=TRUE, a matrix of local influence and total local influence measures (under the case-weight perturbation scheme) asociated with the (entire) vector of parameters and based on the conformal normal curvature.
• pr.theta
  if local.influence=TRUE, a matrix of local influence and total local influence measures (under the response perturbation scheme) asociated with the (entire) vector of parameters and based on the conformal normal curvature.

Details

The argument formula comprises three parts (separated by the symbols "~" and "|"), namely: observed response variable, predictor of the location submodel (having identity link) and predictor of the dispersion submodel (having logarithmic link). A non-parametric effect may be specified in the predictors, either approximated by a natural cubic spline or a P-spline through the functions ncs() or psp(), respectively. The iterative estimation process is based on the Fisher scoring and backfitting algorithms. Because some distributions such as Student-t, contaminated normal, power exponential, slash and symmetric hyperbolic may be obtained as a scale mixture of normal distributions, the Expectation-Maximization algorithm is applied in those cases to obtain a more efficient iterative process for the parameter estimation. Furthermore, because the Sinh-t distribution can be obtained as a scale mixture of Sinh-normal distributions, the Expectation-Maximization algorithm is also applied in that case to obtain a more efficient iterative process for the parameter estimation. The smoothing parameter(s) is(are) chosen using the unweighted cross-validation score. The function ssym.l() calculates deviance-type residuals for both submodels as well as local influence measures under case-weight and response perturbation schemes.

References

Vanegas, L.H. and Paula, G.A. (2014a) A Semiparametric Approach for Joint Modeling of Median and Skewness. TEST (accepted) Vanegas, L.H. and Paula, G.A. (2014b) Log-symmetric distributions: statistical properties and parameter estimation. Brazilian Journal of Probability and Statistics (submitted)

See Also

ssym.nl

Examples

###################################################################################
########### Fraction of Cell Volume Data - a Power-exponential model  ###########
###################################################################################

data("Ovocytes", package="ssym")
fit <- ssym.l(fraction ~ type + psp(time) | type + psp(time), data=Ovocytes,
                family='Powerexp', xi=-0.65, local.influence=TRUE)
summary(fit)

################## Plot of the non-parametric effects ##################

par(mfrow=c(1,2))
np.graph(fit, which=1)
np.graph(fit, which=2, exp=TRUE)

################## Plot of deviance-type residuals ##################

plot(fit)

################## Plot of local influence measures ##################

ilm <- influence.ssym(fit)

###################################################################################
################## Biaxial Fatigue Data - a Birnbaum-Saunders model   #############
###################################################################################

data("Biaxial", package="ssym")
fit <- ssym.l(log(Life) ~ log(Work), family='Sinh-normal', xi=0.41, data=Biaxial, 
              local.influence=TRUE)
summary(fit)

################## Plot of the fitted model ##################

xl <- "Work per cycle"
rx <-range(Biaxial$Work)
ry <- range(Biaxial$Life)
plot(Biaxial$Work,Biaxial$Life,xlim=rx,ylim=ry,type="p",cex=0.3,lwd=3,ylab="",xlab="")
par(new=TRUE)
ids <- sort(Biaxial$Work, index=TRUE)$ix
plot(Biaxial$Work[ids],exp(fitted(fit)$mu[ids]),xlim=rx,ylim=ry,type="l",ylab="Life",xlab=xl)

################## Plot of deviance-type residuals ##################

plot(fit)

################## Plot of local influence measures ##################

ilm <- influence.ssym(fit)