RCTS (version 0.2.4)

iterate: Wrapper around estimate_beta(), update_g(), and estimating the factorstructures.

Description

Wrapper around estimate_beta(), update_g(), and estimating the factorstructures.

Usage

iterate(
  Y,
  X,
  beta_est,
  g,
  lambda_group,
  factor_group,
  lambda,
  comfactor,
  S,
  k,
  kg,
  robust,
  method_estimate_beta = "individual",
  method_estimate_factors = "macro",
  verbose = FALSE
)

Value

list with

1. estimated beta

2. vector with group membership

3. matrix with the common factor(s) (contains zero's if there are none estimated)

4. loadings to the common factor(s)

5. list with the group specific factors for each of the groups

6. data.frame with loadings to the group specific factors augmented with group membership and id (to have the order of the time series)

7. the value of the objective function

Arguments

Y

Y: NxT dataframe with the panel data of interest

X

X: NxTxp array containing the observable variables

beta_est

estimated values of beta

g

Vector with estimated group membership for all individuals

lambda_group

loadings of the estimated group specific factors

factor_group

estimated group specific factors

lambda

loadings of the estimated common factors

comfactor

estimated common factors

S

number of groups to estimate

k

number of common factors to estimate

kg

vector with length S. Each element contains the number of group specific factors to estimate.

robust

TRUE or FALSE: defines using the classical or robust algorithm to estimate beta

method_estimate_beta

defines how beta is estimated. Default case is an estimated beta for each individual. Default value is "individual." Possible values are "homogeneous", "group" or "individual".

method_estimate_factors

specifies the robust algorithm to estimate factors: default is "macro". The value is not used when robust is set to FALSE.

verbose

when TRUE, it prints messages

Examples

set.seed(1)
original_data <- create_data_dgp2(30, 10)
Y <- original_data[[1]]
X <- original_data[[2]]
g <- original_data[[3]]
beta_est <- matrix(rnorm(4 * ncol(Y)), nrow = 4)
factor_group <- original_data[[5]]
lambda_group <- original_data[[6]]
comfactor <- matrix(0, nrow = 1, ncol = ncol(Y))
lambda <- matrix(0, nrow = 1, ncol = nrow(Y))
iterate(Y, X, beta_est, g, lambda_group, factor_group, lambda, comfactor, 3, 0, c(3, 3, 3), TRUE,
  verbose = FALSE)