boot {econet}

boot: Bootstrap residuals with cross-sectional dependence

Description

boot: Bootstrap residuals with cross-sectional dependence

Usage

## S3 method for class 'econet'
boot(
  object,
  hypothesis = c("lim", "het", "het_l", "het_r", "par", "par_split_with",
    "par_split_btw", "par_split_with_btw"),
  group = NULL,
  niter,
  weights = FALSE,
  delta = NULL,
  na.rm = FALSE,
  parallel = FALSE,
  cl,
  ...
)

Arguments

object

an object of class econet obtained using 'NLLS' estimation.

hypothesis

string. One of c("lim","het", "het_l", "het_r", "par", "par_split_with", "par_split_btw", "par_split_with_btw").

group

NULL or vector of positive integers specifying the indices for resampling within groups.

niter

number of required iterations.

weights

logical. It is TRUE if the object object was estimated using weights, and FALSE otherwise. Default FALSE.

delta

Default is NULL.It has to be a number between zero (included) and one (excluded). When used, econet performs a constrained NLLS estimation. In this case, the estimated peer effect parameter, taken in absolute value, is forced to be higher than zero and lower than the spectral radius of G. Specifically, delta is a penalizing factor, decreasing the goodness of fit of the NLLS estimation, when the peer effect parameter approaches one of the two bounds. Observe that very high values of delta may cause NLLS estimation not to converge.

na.rm

logical. Should missing values (including NaN) be removed?

parallel

logical. It is TRUE if the user wants to make use of parallelization. Default is FALSE. Observe that this option is still in its beta version and it has been tested only for the Windows platform.

cl

numeric. Number of cores to be used for parallelization.

...

additional parameters

Details

For additional details, see the vignette (doi:10.18637/jss.v102.i08). Warning: This function is available only when net_dep is run with estimation == "NLLS"

Value

a numeric vector containing bootstrapped standard errors (see Anselin, 1990). If the procedure is not feasible, it returns a vector of NAs.

References

Anselin, L., 1990, "Some robust approach to testing and estimation in spatial econometrics", Regional Science and Urban Economics, 20, 141-163.

See Also

net_dep

Examples

# Load data
data("db_cosponsor")
data("G_alumni_111")
db_model_B <- db_cosponsor
G_model_B <- G_cosponsor_111
G_exclusion_restriction <- G_alumni_111
are_factors <- c("party", "gender", "nchair")
db_model_B[are_factors] <- lapply(db_model_B[are_factors], factor)

# Specify formula
f_model_B <- formula("les ~gender + party + nchair")

# Specify starting values
starting <- c(alpha = 0.23952,
              beta_gender1 = -0.22024,
              beta_party1 = 0.42947,
              beta_nchair1 = 3.09615,
              phi = 0.40038,
              unobservables = 0.07714)

# object Linear-in-means model
lim_model_B <- net_dep(formula = f_model_B, data = db_model_B,
                       G = G_model_B, model = "model_B", estimation = "NLLS",
                       hypothesis = "lim", endogeneity = TRUE, correction = "heckman",
                       first_step = "standard",
                       exclusion_restriction = G_exclusion_restriction,
                       start.val = starting)
# Bootstrap
# Warning: this may take a very long time to run.
# Decrease the number of iterations to reduce runtime.
# If you run econet on a Windows platform, you can try to set the
# argument parallel = TRUE. However note that this option is still
# in its beta version.
boot_lim_estimate <- boot(object = lim_model_B, hypothesis = "lim",
                          group = NULL, niter = 10, weights = FALSE)
boot_lim_estimate