tvcm: tvcm: Time-Varying Coefficient Models

In inqs909/tvcm: Time-Varying Coefficient Models

Description

This function estimates the time-varying coefficient model at different time points.

Usage

tvcm(
  formula,
  data,
  time,
  id = NULL,
  ngrids = 200,
  grid_points = NULL,
  bandwidth = NULL,
  kernel = "epanechnikov",
  se = FALSE,
  alpha = 0.05,
  nboot = 1000
)

Arguments

formula	A formula class object. Provides information about the names of the response and predictor variables.
data	A data frame containing the variables needed for the function.
time	The name of the variable indicating the time points for each observation.
id	The name of the variable to group observations. Necessary when dealing with repeated measurements such as longitudinal data.
ngrids	When specified, a vector of size ngrid is created for the varying-coefficient values. The default value is 200. The vector is creates using the maximum and minimum from the provided time points.
grid_points	A vector indicating the grid points to estimate the varying coefficient values. When specified, ngrid is ignored.
bandwidth	A numeric value indicating the bandwidth. Default is the tenth of the range of the time points.
kernel	The name of the kernel function used to estimate the varying-coefficient values. Default is Epanechnikov.
se	If set TRUE, a bootstrap method is applied to estimate the standard errors and percentiles.
alpha	A value indicating the significance level for the percentiles.
nboot	A number indicating how many boot samples to construct.

Value

tvcm returns a list containing the estimated varying coefficients

• estimates: A list containing two matrices:

  • est: a matrix for the estimates, each row represents the estimate of the varying coefficient

  • deriv: a matrix for the first derivative, each row represents the derivative of the varying coefficient

• bootstrap_results: If specified, a list containing the elements below

  • boot_se: A list containing two matrices for the standard errors:

    • est: a matrix for the estimates, each row represents the estimate of the varying coefficient

    • deriv: a matrix for the first derivative, each row represents the derivative of the varying coefficient

  • boot_lower: A list containing two matrices for the lower percentiles:

    • est: a matrix for the estimates, each row represents the estimate of the varying coefficient

    • deriv: a matrix for the first derivative, each row represents the derivative of the varying coefficient

  • boot_upper:A list containing two matrices for the upper percentiles:

    • est: a matrix for the estimates, each row represents the estimate of the varying coefficient

    • deriv: a matrix for the first derivative, each row represents the derivative of the varying coefficient

  • boot_samples: An array containing the bootstrap samples

• time_points: The time points used for the estimates

Author(s)

Isaac Quintanilla Salinas

Examples

tvcm(formula = Y~x1+x2, data = normal_data, time = time, 
     id = id, se = TRUE, nboot = 100)

inqs909/tvcm documentation built on Dec. 20, 2021, 7:03 p.m.