cpm: Least squares estimates of a constrained polynomial...

In bonStats/gcreg: General Constraint REGression

Description

Estimates univariate polynomials with parameters from a closed convex set. Some examples are shape constraints (e.g. montonicity, convexity) or simply linear parameter constraints such as β [1] >= 0.

Usage

cpm(formula, data, subset, weights, na.action, degree, constraint = NULL,
  oracle = NULL, start, c_region = c(-Inf, Inf), ...)

Arguments

formula	an object of class formula (or one that can be coerced to that class): a symbolic description of the model to be fitted.
data	an optional data frame, list or environment (or object coercible by as.data.frame to a data frame) containing the variables in the model. If not found in data, the variables are taken from environment(formula), typically the environment from which the function is called.
subset	NOT YET IMPLEMENTED an optional vector specifying a subset of observations to be used in the fitting process.
weights	NOT YET IMPLEMENTED.
na.action	a function which indicates what should happen when the data contain NAs. The default is set by the na.action setting of options, and is na.fail if that is unset. The 'factory-fresh' default is na.omit. Another possible value is NULL, no action. Value na.exclude can be useful.
degree	degree of polynomial to be fit.
constraint	an optional character string of "monotone" ("convex" coming soon).
oracle	an optional function of class oracle, returning TRUE when a given point is inside the constrained set and FALSE otherwise. See make_oracle.
start	intial value of COLS optimisation.
c_region	the applicable region for the constraint, default is c(-Inf,Inf), the real line.
...	arguments to be passed to cols_control.

Value

Constrained regression model with class creg. Currently a named list including objects: beta (parameter vector), fitted.values, residuals, and RSS.

Examples

## Not run: 
md <- cpm(y ~ x, degree = 5, constraint = "monotone", c_region = c(0,1))
print(md)
coef(md)
residuals(md)
fitted(md)

library(polynom)
fitted_pl <- polynomial(coef(md))
plot(fitted_pl, c(0,1))

## End(Not run)

bonStats/gcreg documentation built on May 20, 2019, 5:44 p.m.