| Type: | Package |
| Title: | An R Package for Fitting Separable Nonlinear Models |
| Version: | 0.2.0 |
| Author: | Mariano Rodriguez-Arias <arias@unex.es>, Juan Antonio Fernandez <jfernandck@alumnos.unex.es>, Javier Cabello <coco@unex.es>, Rafael Benitez <rabesua@uv.es> |
| Maintainer: | Rafael Benitez <rabesua@uv.es> |
| Description: | Set of functions implementing the algorithm described in Fernandez Torvisco et al. (2018) for fitting separable nonlinear regression curves. See Fernandez Torvisco, Rodriguez-Arias Fernandez and Cabello Sanchez (2018) <doi:10.2298/FIL1812233T>. |
| Encoding: | UTF-8 |
| RoxygenNote: | 7.2.3 |
| License: | GPL-3 |
| Imports: | Deriv, foreach, stringr, methods |
| Suggests: | testthat (≥ 3.0.0) |
| Config/testthat/edition: | 3 |
| NeedsCompilation: | no |
| Packaged: | 2023-04-11 14:54:00 UTC; rbens |
| Repository: | CRAN |
| Date/Publication: | 2023-04-11 15:20:02 UTC |
Extract Model Deviance for a nsltac fit model
Description
Returns the model deviance of the fit.
Usage
## S3 method for class 'nlstac'
deviance(object, ...)
Arguments
object |
An object of class |
... |
Ignored, for compatibility issues. |
Value
A single numeric value for the deviance of the model
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Residuals Degree-of-Freedom of a nsltac Fit
Description
Returns the residuals degrees-of-freedom from a nlstac model fit.
Usage
## S3 method for class 'nlstac'
df.residual(object, ...)
Arguments
object |
An object of class |
... |
Ignored, for compatibility issues. |
Value
A single numeric value for the deviance of the model
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Extract Fitted Values from a nsltac Fit
Description
Returns the fitted values from an object returned by a nlstac model fit.
Usage
## S3 method for class 'nlstac'
fitted(object, ...)
Arguments
object |
An object of class |
... |
Ignored, for compatibility issues. |
Value
A single numeric value for the deviance of the model
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Get best-fit parameters
Description
Returns the best-fit parameters for a given nonlinear parameter bounds and nonlinear functions.
Usage
get_best_params(
dat,
form,
functions,
nlparam,
lp,
lp_bounds = NULL,
lhs_var,
N = 10,
silent = TRUE,
parallel = FALSE
)
Arguments
dat |
Data frame with the data points to be fitted. |
form |
A formula given in the form "LHS ~ a1 * F_1(x,p1) + a2 * F_2(x,p2) + ... + an F_n(x,pn)" |
functions |
A string array with the nonlinear functions as obtained with |
nlparam |
A list with the names of the nonlinear parameters and their lower and upper bounds in the form |
lp |
A string array with the names of the linear parameters contained in the formula as obtained with |
lp_bounds |
An optional list with the bounding restrictions over the linear parameters. |
lhs_var |
The name of the left-hand-side of the formula |
N |
Size of the partition of the nonlinear parameters. Defaults to 10. |
silent |
Logical. If TRUE (default) supresses any warnings regarding the collinearity of the columns of the matrix in the determination of the best linear parameters. |
parallel |
Logical. If TRUE then multicore parallelization of for loops is done with the parallel package. Defaults to FALSE. |
Details
This is an internal function called from nls_tac function. It is not intended for direct use.
Value
A list containing the strings for the nonlinear functions of the formula.
Get nonlinear functions from a separable nonlinear formula
Description
Returns the nonlinear functions of a formula as charater strings.
Usage
get_functions(form, lp)
Arguments
form |
Either a string in the form |
lp |
A string array with the names of the linear parameters contained in the formula as obtained with |
Details
This is an internal function used by nls_tac. A separable nonlinear formula is of the form
y ~ a_1 f_1(x;p) + a_2 f_2(x;p) + \ldots + a_n f_n(x;p),
where f_1,..., f_n are general nonlinear functions, a_1,...,a_n, are the linear coefficients and p is the vector of nonlinear parameters.
The formula given in the input should be of this form and get_functions will return an array with the string expressions of functions f_i.
Value
An array containing the strings for the nonlinear functions of the formula.
Note
Also formulas of the form
y ~ a_1/f_1(x;p) + a_2/f_2(x;p) + \ldots
could be given.
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Get left hand side of a formula
Description
Returns the dependent variable in a formula given by a string or a formula
Usage
get_lhs(form)
Arguments
form |
Either a string in the form |
Value
A string with the name of the left hand side variable in the formula
Get parameters from a formula
Description
Returns the linear and nonlinear parameters of a formula
Usage
get_parameters(form, var_names)
Arguments
form |
Either a string in the form |
var_names |
A string array with the column names of the data.frame containing the data to be fitted. |
Value
A list containing the names of the linear and the nonlinear parameters of the formula.
Get right hand side of a formula
Description
Returns the dependent variable in a formula given by a string or a formula
Usage
get_rhs(form)
Arguments
form |
Either a string in the form |
Value
A string with the name of the left hand side variable in the formula
Is nlsTAC class check
Description
Checks wether an R object is of tac class or not.
Usage
is.nlstac(x)
Arguments
x |
Any R object. |
Value
Returns TRUE if its argument is a tac object (that is, has "tac"
amongst its classes) and FALSE otherwise.
Extract Log-Likelihood from a nlstac Model
Description
Returns the log-likelihood value from an object returned by a nlstac model fit.
Usage
## S3 method for class 'nlstac'
logLik(object, ...)
Arguments
object |
An object of class |
... |
Ignored, for compatibility issues. |
Value
A single numeric value for the log-likelihood of the model
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Nonlinear fit with the TAC algorithm
Description
Fits a nonlinear function to data.
Usage
nls_tac(
formula,
data = parent.frame(),
functions = NULL,
nlparam,
lp_bounds = NULL,
N = 10,
tol = 1e-04,
parallel = FALSE,
maxiter = 50,
quiet = FALSE,
silent = TRUE,
compute_errors = TRUE
)
Arguments
formula |
A formula given in the form "LHS ~ a1 * F_1(x,p1) + a2 * F_2(x,p2) + ... + an F_n(x,pn)" |
data |
Data frame with the data points to be fitted. |
functions |
A string array with the nonlinear functions. If |
nlparam |
A list with the names of the nonlinear parameters and their lower and upper bounds in the form |
lp_bounds |
An optional list with the bounding restrictions over the linear parameters. |
N |
Size of the partition of the nonlinear parameters. Defaults to 10. |
tol |
Stopping condition. The algorithm stops whenever the maximum difference between two consecutive iterations is less than |
parallel |
Logical. If TRUE then multicore parallelization of for loops is done with the parallel package. Defaults to FALSE. |
maxiter |
Integer. The maximum number of iterations. Defaults to 50. |
quiet |
Logical. If TRUE, all progress messages are supressed (defaults to FALSE). |
silent |
Logical. Parameter to be passed to get_best_parameters function. If TRUE (default) suppresses any warnings regarding the collinearity of the columns of the matrix in the determination of the best linear parameters. |
compute_errors |
Logical. If TRUE (default value) the function computes the standard error of the estimates. |
Value
An object of class nlstac. A list of
coefficients |
Best coefficients obtained. |
stdError |
Standard errors for the obtained coefficients |
convInfo |
Convergence information: a list with the number of iterations performed ( |
SSR |
Sum of the squares of the residuals |
resid |
Residuals |
data |
Data frame used. Columns of variables not used in the formula fitted will be removed |
formula |
Formula used |
df |
Degrees of freedom |
sigma |
Standard deviation estimate. |
Rmat |
R matrix in the QR decomposition of the gradient matrix used for the computation of the standard errors of the coefficients |
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
References
Fernández Torvisco, J. A.; Rodríguez-Arias Fernández, M.; Cabello Sánchez, J. (2018). “A New Algorithm to Fit Exponential Decays without Initial Guess”, Filomat 32:12, 4233–4248.
Bates, D. M. and Watts, D. G. (1988) Nonlinear Regression Analysis and Its Applications, Wiley
Examples
### Examples from 'nls' doc ###
DNase1 <- subset(DNase, Run == 1)
## using logistic formula
fm2DNase1 <- nls_tac(density ~ Asym/(1 + exp((xmid - log(conc))/scal)),
data = DNase1,
nlparam = list(xmid = c(1e-7,10), scal = c(1e-7,3)))
## some generics are applicable
coefficients(fm2DNase1)
summary(fm2DNase1)
## obtaining extra information
fm2DNase1$resid # residuals
fm2DNase1$formula # formula used
fm2DNase1$df # degrees of freedom
fm2DNase1$convInfo # Convergence information (n. iterations, tolerance attained)
fm2DNase1$SSR # SSR
fm2DNase1$data$density - fm2DNase1$resid # fitted values
## Synthetic examples
## Double exponential
x <- seq(from = 0, to = 20, length.out = 1000)
y <- 3*exp(-0.12*x) + 0.6*exp(-3.05*x) + 5 + 0.1*rnorm(length(x))
df <- data.frame(time = x, Temp = y)
# The nonlinear parameter list (with lower and upper values)
nlparam <- list(b1 = c(0,2), b2 = c(0,8))
fittac <- nls_tac('Temp ~ a1*exp(-b1*time) + a2*exp(-b2*time) + a3',
data = df,
nlparam = nlparam,
N = 5)
summary(fittac)
plot(Temp ~ time, data = df)
lines(x, predict(fittac), col = "red", lwd = 2)
##
N <- 100
x <- seq(from = 0, to = 3, length.out = N)
y <- 3*sin(5*x)^2 + 2 + 0.2*rnorm(N)
df <- data.frame(x = x, y = y)
form <- y ~ a1*sin(b1*x)^2 + a2
nlbnds <- list(b1 = c(0.5,10)) # rough bouds for tac
tac_model <- nls_tac(formula = form,
data = df,
nlparam = nlbnds,
N = 10,
tol = 1e-5)
yhat <- predict(tac_model)
plot(x,y)
lines(x,yhat, col = "blue")
Extract the Number of Observations from a nsltac Fit
Description
Returns the number of observations from a nlstac model fit.
Usage
## S3 method for class 'nlstac'
nobs(object, ...)
Arguments
object |
An object of class |
... |
Ignored, for compatibility issues. |
Value
A single numeric value for the deviance of the model
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Predict a nls tac fit.
Description
Returns the prediction values of a nls tac fit model for a given set of predictors.
Usage
## S3 method for class 'nlstac'
predict(object, newdata = NULL, ...)
Arguments
object |
An object of class |
newdata |
An optional data frame in which to look for variables with which to predict. It should contain
at least the columns for the independent variables with the same names as the ones used in the formula passed to the
|
... |
Ignored, for compatibility issues. |
Value
A vector with the predicted values for the predictor given in the newdata input.
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Examples
x <- seq(from = 0, to = 3, length.out = 50)
y <- 3*exp(-5*x) + 2*x + 1 + 0.05*rnorm(50)
df <- data.frame(x = x, y = y)
form <- y ~ a1*exp(-b1*x) + a2*x + a3
nlbnds <- list(b1 = c(0.5,10)) # bouds for tac
fitmodel <- nls_tac(formula = form, data = df, nlparam = nlbnds)
yhat <- predict(fitmodel) # predict values in the fitted abcisae
plot(x,y)
lines(x,yhat, col = "red", lwd = 2)
# Predicting for other points
newdata <- c(0.25,1.5,2.25)
yhat2 <- predict(fitmodel, newdata = data.frame(x = newdata))
points(newdata, yhat2, pch = 19, col = "blue", cex = 1.2)
Print a nlstac Model
Description
Standard method for overriding the print.list method for nlstac model fit.
Usage
## S3 method for class 'nlstac'
print(x, digits = max(3L, getOption("digits") - 3L), ...)
Arguments
x |
An object of class |
digits |
a positive integer indicating how many significant digits are to be shown. |
... |
Ignored, for compatibility issues. |
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Prints the summary a summary.nlstac object.
Description
Internal function for printing the summary of a nlstac.
Usage
## S3 method for class 'summary.nlstac'
print(
x,
digits = max(3L, getOption("digits") - 3L),
signif.stars = getOption("show.signif.stars"),
...
)
Arguments
x |
An object of class |
digits |
Number of significant digits to be shown (defaults to 3). |
signif.stars |
logical. If TRUE, ‘significance stars’ are printed for each coefficient. |
... |
Ignored, for compatibility issues. |
Extract Model Residuals for a nsltac fit model
Description
Returns the model residuals of the fit.
Usage
## S3 method for class 'nlstac'
residuals(object, ...)
Arguments
object |
An object of class |
... |
Ignored, for compatibility issues. |
Value
A vector with the residual values.
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Summary a nls tac fit.
Description
Gives the fitted coefficients and the convergence information of the fit.
Usage
## S3 method for class 'nlstac'
summary(object, ...)
Arguments
object |
An object of class |
... |
Ignored, for compatibility issues. |
Value
Returns, via the print.nlstac function the following items:
- Formula: The formula fitted to the data
- Parameters: The value of the estimated parameters (Estimated) together
with their standard errors (Std. Error), and their statistical
significance (t value, Pr(>|t|), signif. stars)
- SSR and df.
- Convergence information: N. of iterations and the tolerance achieved.
Calculate Variance-Covariance Matrix for a nlstac Fitted Model Object
Description
Returns the variance-covariance matrix of the main parameters of a fitted model object. The “main” parameters of model correspond to those returned by coef,
Usage
## S3 method for class 'nlstac'
vcov(object, ...)
Arguments
object |
An object of class |
... |
Ignored, for compatibility issues. |
Value
A matrix of the estimated covariances between the parameter estimates.
Author(s)
Mariano Rodríguez-Arias (arias@unex.es). Deptartment of Mathematics
Juan Antonio Fernández Torvisco (jfernandck@alumnos.unex.es). Department of Mathematics
University of Extremadura (Spain)
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)