TempDisaggDGP: High and low-frequency data generating processes

In kavehsn/HDTempDisagg: High-dimensional temporal disaggregation

Description

This function generates the high-frequency mn_l \times 1 response vector y, according to y=Xβ+ε, where X is an mn_l\times p matrix of indicator series, and the mn_l\times 1 coefficient vector may be sparse. The low-frequency n_l\times 1 vector can be generated by pre-multiplying a disaggregation matrix n_l\times mn_l matrix, such that the sum, the average, the last or the first value of y equates the corresponding Y observation (see \insertCitesax2013temporal;textualHDTempDisagg).

Usage

TempDisaggDGP(
  n_l,
  m,
  p = 1,
  beta = 0.5,
  sparsity = 1,
  method = "Denton-Cholette",
  annualMat = "sum",
  rho = 0,
  mean_X = 0.5,
  sd_X = 1,
  sd_e = 1,
  simul = FALSE
)

Arguments

n_l	size of the low frequency series
m	the integer multiple for generating the high-frequency series
beta	the positive and negative beta elements for the coefficient vector
sparsity	sparsity percentage of the coefficient vector
method	nominates the choice of the DGP
annualMat	choice of the disaggregation matix
rho	the autocorrelation coefficient
mean_X	mean of the design matrix
sd_X	standard deviation of the design matrix
sd_e	standard deviation of the errors
simul	when TRUE the design matrix and the coefficient vector are fixed

References

\insertAllCited

Examples

TempDisaggDGP(n_l = 10, m = 4, p = 4, method = 'Chow-Lin', annualMat = 'sum', mean_X = 0.5, sd_X = 1, sd_e = 1 , rho = 0.5)

kavehsn/HDTempDisagg documentation built on Dec. 21, 2021, 5:21 a.m.