Package 'modelObj'

Create an Object of Class modelObj

Description

A utility function to transfer user defined models and estimation methods to an object of class modelObj.

Usage

buildModelObj(
  model,
  solver.method = NULL,
  solver.args = NULL,
  predict.method = NULL,
  predict.args = NULL
)

Arguments

model	An object of class formula; the model.
solver.method	An object of class character specifying the name of the R function to be used to obtain parameter estimates. Or, the function to be used to obtain parameter estimates. For example, ‘lm’, ‘glm’, or ‘rpart’. The specified modeling function MUST have a corresponding predict method.
solver.args	An object of class list containing additional arguments to be sent to solver.method. Arguments must be provided as a list, where the name of each element matches a formal argument of solver.method. For example, if a logistic regression using glm is desired, $solver.method = ``glm"$ $solver.args = list(``family"=binomial)$ A solver.method can takes formal arguments 'formula' and 'data' as inputs, such as lm and glm. Some R methods do not use formal names 'formula' and 'data'; a user can indicate if a different naming convention is used for these two input arguments. For example, if a method expects the formula object to be passed through input variable x, solver.args <- list("x"="formula") A solver.method can also take formal arguments 'x' and 'y' as inputs, such as glmnet. Some R methods do not use formal names 'x' and 'y' to indicate the covariate and response; a user can indicate if a different naming convention is used for these two input arguments. For example, if a method expects the covariate matrix to be passed through input variable X, solver.args <- list("X"="x")
predict.method	A character. The name of the R function or the function to be used to obtain predictions. For example, ‘predict.lm’, ‘predict’, or ‘predict.glm’. If no function is explicitly given, the generic predict is assumed. For many methods, the generic method is appropriate.
predict.args	A list. Additional arguments to be sent to predict.method. This must be provided as a list, where the name of each element matches a formal argument of predict.method. For example, if a logistic regression using glm was used to fit the model formula object and predictions on the scale of the response are desired, $predict.method = ``predict.glm"$ $predict.args = list(``type"=``response").$ It is assumed that the predict.method has formal arguments “object" and “newdata". If predict.method does not use these formal arguments, predict.args must explicitly indicate the variable names used for these inputs. For example, list(“newx"=“newdata") if the new data is passed to predict.method through input argument “newx".

Details

Unless changed by the user in solver.args and/or predict.args, default settings are assumed for the specified regression and prediction methods.

Value

An object of class modelObjFormula or modelObjXY, which inherit directly from modelObj.

Examples

#----------------------------------------------------#
   # Create modeling object using a formula
   #----------------------------------------------------#
   mo <- buildModelObj(model=Y ~ X1 + X2 + X3 + X4,
                       solver.method='lm', 
                       predict.method='predict.lm',
                       predict.args=list(type='response'))

---

Obtain parameter estimates

Description

Performs specified regression analysis.

Usage

fit(object, data, response, ...)

## S4 method for signature 'modelObj,data.frame'
fit(object, data, response, ...)

Arguments

object	An object of class modelObj as returned by the buildModelObj function.
data	An object of class data.frame containing the variables in the model.
response	An object of class vector containing the response variable.
...	ignored

Details

If defined by the modeling function, the following methods can be applied to the value object returned: coef, plot, predict, print, residuals, show, and summary.

Value

An object of class modelObjFit, which contains the object returned by the modeling function and the method to be used to obtain predictions.

Examples

# generate data
   X <- matrix(rnorm(1000,0,1),
               ncol=4,
               dimnames=list(NULL,c("X1","X2","X3","X4")))

   Y <- X %*% c(0.1, 0.2, 0.3, 0.4) + rnorm(250)

   X <- data.frame(X)

   # create modeling object using a formula
   mo <- buildModelObj(model=Y ~ X1 + X2 + X3 + X4,
                  solver.method='lm')

   # fit model
   fit.obj <- fit(object=mo, data=X, response=Y)

   coef(fit.obj)
   head(residuals(fit.obj))
   plot(fit.obj)
   head(predict(fit.obj,X))
   summary(fit.obj)

---

Retrieve Regression Object

Description

Retrieves the value object returned by the regression method used to obtain parameter estimates.

Usage

fitObject(object, ...)

## S4 method for signature 'ANY'
fitObject(object, ...)

## S4 method for signature 'modelObjFit'
fitObject(object, ...)

Arguments

object	An object of class modelObjFit.
...	ignored.

Details

This function is useful for accessing methods that are defined by the regression method but are not directly accessible from the modelObjFit object. For example, for many regression methods, users can retrieve the fitted values by calling fitted.values(object). This method is not directly accessible from a modelObjFit. However, fitted.values() can be applied to the object returned by fitObject().

Value

The Value returned by the regression method specified in the governing modelObj. The exact structure of the value will depend on the regression method. For example, if nls() is the regression method, a list is returned.

Examples

# Generate data
   X <- matrix(rnorm(1000,0,1),
               ncol=4,
               dimnames=list(NULL,c("X1","X2","X3","X4")))

   Y <- X %*% c(0.1, 0.2, 0.3, 0.4) + rnorm(250)

   X <- data.frame(X)

   # Create modeling object using a formula
   mo <- buildModelObj(model=Y ~ X1 + X2 + X3 + X4,
                       solver.method='lm')

   # Fit model
   fit.obj <- fit(object=mo, data=X, response=Y)

   obj <- fitObject(fit.obj)
   fobj <- fitted.values(obj)
   head(fobj)

---

Retrieve model

Description

Retrieves model from modelObj

Usage

model(object, ...)

## S4 method for signature 'ANY'
model(object, ...)

## S4 method for signature 'modelObj'
model(object, ...)

## S4 method for signature 'modelObjFit'
model(object, ...)

Arguments

object	A modelObj object
...	ignored

Value

The formula for the regression

---

Class modelObj

Description

A class for model objects.

Details

Objects should not be created directly. The utility function buildModelObj() should be used.

Slots

model

Object of class formula

solver

Object of class methodObjSolver method to obtain parameter estimates.

predictor

Object of class methodObjPredict method to obtain predicted values.

Methods

fit

: Executes regression step.

model

: Retrieve model.

solver

: Retrieve regression method name.

solverArgs

: Retrieve arguments to be sent to regression method.

solverArgs(object)<-

: Set arguments to be sent to regression method.

predictor

: Retrieve prediction method name.

predictorArgs

: Retrieve arguments to be sent to prediction method.

predictorArgs(object)<-

: Set arguments to be sent to prediction method.

Examples

showClass("modelObj")

---

Class modelObjFit

Description

A class for storing regression analysis results.

Usage

## S4 method for signature 'modelObjFit'
coef(object, ...)

## S4 method for signature 'modelObjFit'
plot(x, y, ...)

## S4 method for signature 'modelObjFit'
print(x)

## S4 method for signature 'modelObjFit'
residuals(object, ...)

## S4 method for signature 'modelObjFit'
show(object)

## S4 method for signature 'modelObjFit'
summary(object, ...)

Arguments

object	An object of class modelObjFit
...	passed to underlying method defined for regression value object.
x	An object of class modelObjFit
y	ignored

Methods (by generic)

• coef: Extract Model Coefficients

• plot: X-Y plotting

• print: Print regression results

• residuals: Extract residuals

• show: Show regression results

• summary: Show summary results

Slots

fitObj

Object returned by the regression analysis

modelObj

Object of class modelObj.

Methods

fitObject

: Extracts regression step.

model

: Retrieve model.

solver

: Retrieve regression method name.

solverArgs

: Retrieve arguments to be sent to regression method.

solverArgs(object)<-

: Set arguments to be sent to regression method.

predictor

: Retrieve prediction method name.

predictorArgs

: Retrieve arguments to be sent to prediction method.

predictorArgs(object)<-

: Set arguments to be sent to prediction method.

Examples

showClass("modelObjFit")

---

Model Predictions

Description

Predictions from the results of a fit object.

Usage

predict(object, ...)

## S4 method for signature 'modelObjFit'
predict(object, newdata, ...)

Arguments

object	An object of class modelObjFit as returned by the fit() function.
newdata	An object of class data.frame containing the variables in the model.
...	ignored

Value

Model predictions, the form of which depend on the regression analysis.

Examples

# generate data
   X <- matrix(rnorm(1000,0,1),
               ncol=4,
               dimnames=list(NULL,c("X1","X2","X3","X4")))

   Y <- X %*% c(0.1, 0.2, 0.3, 0.4) + rnorm(250)

   X <- data.frame(X)

   # create modeling object using a formula
   mo <- buildModelObj(model=Y ~ X1 + X2 + X3 + X4,
                  solver.method='lm')

   # fit model
   fit.obj <- fit(object=mo, data=X, response=Y)

   predict(fit.obj)
   predict(fit.obj, newdata = X[1:10,])

---

Retrieve Prediction Method

Description

Retrieves method for prediction analysis

Usage

predictor(object, ...)

## S4 method for signature 'modelObj'
predictor(object, ...)

## S4 method for signature 'modelObj'
predictor(object, ...)

## S4 method for signature 'modelObjFit'
predictor(object, ...)

Arguments

object	A modelObj object
...	ignored

Value

An object of class character or function

---

Retrieve Predictor Arguments

Description

Retrieves the arguments that are to be passed to the prediction method when called.

Usage

predictorArgs(object, ...)

## S4 method for signature 'modelObj'
predictorArgs(object, ...)

predictorArgs(object) <- value

## S4 replacement method for signature 'ANY,ANY'
predictorArgs(object) <- value

## S4 replacement method for signature 'modelObj,list'
predictorArgs(object) <- value

## S4 method for signature 'modelObjFit'
predictorArgs(object, ...)

Arguments

object	A modelObj object
...	ignored
value	List to be stored in args

Value

A list

---

Retrieve Solver Method

Description

Retrieves method for regression analysis

Usage

solver(object, ...)

## S4 method for signature 'ANY'
solver(object, ...)

## S4 method for signature 'modelObj'
solver(object, ...)

## S4 method for signature 'modelObjFit'
solver(object, ...)

Arguments

object	A modelObj object
...	ignored

Value

An object of class character or function

---

Retrieve Solver Arguments

Description

Retrieves the arguments that are to be passed to the regression method when called.

Usage

solverArgs(object, ...)

## S4 method for signature 'ANY'
solverArgs(object, ...)

## S4 method for signature 'modelObj'
solverArgs(object, ...)

solverArgs(object) <- value

## S4 replacement method for signature 'ANY,ANY'
solverArgs(object) <- value

## S4 replacement method for signature 'modelObj,list'
solverArgs(object) <- value

## S4 method for signature 'modelObjFit'
solverArgs(object, ...)

Arguments

object	A modelObj object
...	ignored
value	List to be stored in args

Value

A list

---