Globallm: Global testing procedure for testing functional-on-scalar...
In alessiapini/fdatest: Interval Wise Testing for Functional Data

Globallm

R Documentation

Global testing procedure for testing functional-on-scalar linear models

Description

The function is used to fit and test functional linear models. It can be used to carry out regression, and analysis of variance. It implements the global testing procedure for testing the significance of the effects of scalar covariates on a functional population.

Usage

Globallm(
  formula,
  B = 1000,
  method = "residuals",
  dx = NULL,
  recycle = TRUE,
  stat = "Integral"
)

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. Example: y ~ A + B where: y is a matrix of dimension n * p containing the point-wise evaluations of the n functional data on p points or an object of class `fd` (see `fda` package) containing the functional data set A, B are n-dimensional vectors containing the values of two covariates. Covariates may be either scalar or factors.
`B`	The number of iterations of the MC algorithm to evaluate the p-values of the permutation tests. The defualt is `B=1000`.
`method`	Permutation method used to calculate the p-value of permutation tests. Choose "`residuals`" for the permutations of residuals under the reduced model, according to the Freedman and Lane scheme, and "`responses`" for the permutation of the responses, according to the Manly scheme.
`dx`	step size for the point-wise evaluations of functional data. dx is only used ia an object of class 'fd' is provided as response in the formula.
`stat`	Type of test statistic used for the global test. Possible values are: `'Integral'` (default) for the integral over the domain of the F- and t-test statistics; `'Max'` for max over the domain of the F- and t-test statistics.

Value

Globallm returns an object of class "IWTlm". The function summary is used to obtain and print a summary of the results. This object is a list containing the following components:

`call`	call of the function.
`design_matrix`	design matrix of the linear model.
`unadjusted_pval_F`	unadjusted p-value function of the F test.
`adjusted_pval_F`	adjusted p-value function of the F test.
`unadjusted_pval_part`	unadjusted p-value functions of the functional t-tests on each covariate, separately (rows) on each domain point (columns).
`adjusted_pval_part`	adjusted p-values of the functional t-tests on each covariate (rows) on each domain point (columns).
`Global_pval_F`	Global p-value of the overall test F.
`Global_pval_part`	Global p-value of t-test involving each covariate separately.
`data.eval`	evaluation of functional data.
`coeff.regr.eval`	evaluation of the regression coefficients.
`fitted.eval`	evaluation of the fitted values.
`residuals.eval`	evaluation of the residuals.
`R2.eval`	evaluation of the functional R-suared.

References

Abramowicz, K., Pini, A., Schelin, L., Stamm, A., & Vantini, S. (2022). “Domain selection and familywise error rate for functional data: A unified framework. Biometrics 79(2), 1119-1132.

D. Freedman and D. Lane (1983). A Nonstochastic Interpretation of Reported Significance Levels. Journal of Business & Economic Statistics 1(4), 292-298.

B. F. J. Manly (2006). Randomization, Bootstrap and Monte Carlo Methods in Biology. Vol. 70. CRC Press.

Examples

# Importing the NASA temperatures data set
data(NASAtemp)
# Defining the covariates
temperature <- rbind(NASAtemp$milan,NASAtemp$paris)
groups <- c(rep(0,22),rep(1,22))

# Performing the IWT
Global.result <- Globallm(temperature ~ groups,B=1000)
# Summary of the IWT results
summary(Global.result)

# Plot of the IWT results
layout(1)
plot(Global.result,main='NASA data', plot_adjpval = TRUE,xlab='Day',xrange=c(1,365))

# All graphics on the same device
layout(matrix(1:6,nrow=3,byrow=FALSE))
plot(Global.result,main='NASA data', plot_adjpval = TRUE,xlab='Day',xrange=c(1,365))

alessiapini/fdatest documentation built on April 28, 2024, 12:35 a.m.