standard_errors.Rd
Computes standard errors for the quantile regression spacing method using subsampling.
Computes standard errors for the quantile regression spacing method using subsampling.
resample_qs( X, y, weights, sampling_method, alpha, jstar, control, algorithm, draw_weights, var_names, subsample_percent, ... ) weighted_bootstrap( X, y, weights, sampling_method, alpha, jstar, control, algorithm, draw_weights, var_names, subsample_percent, ... ) bootstrap( X, y, weights, sampling_method, alpha, jstar, control, algorithm, draw_weights, var_names, subsample_percent, ... ) subsample( X, y, weights, sampling_method, alpha, jstar, control, algorithm, draw_weights, var_names, subsample_percent, ... ) standard_errors( y, X, cluster_matrix, algorithm, control = qs_control(), std_err_control = std_err_control(), var_names, alpha, jstar, parallel = F, weights = NULL, seed = NULL, ... ) resample_qs( X, y, weights, sampling_method, alpha, jstar, control, algorithm, draw_weights, var_names, subsample_percent, ... ) weighted_bootstrap( X, y, weights, sampling_method, alpha, jstar, control, algorithm, draw_weights, var_names, subsample_percent, ... ) bootstrap( X, y, weights, sampling_method, alpha, jstar, control, algorithm, draw_weights, var_names, subsample_percent, ... ) subsample( X, y, weights, sampling_method, alpha, jstar, control, algorithm, draw_weights, var_names, subsample_percent, ... ) standard_errors( y, X, cluster_matrix, algorithm, control = qs_control(), std_err_control = std_err_control(), var_names, alpha, jstar, parallel = F, weights = NULL, seed = NULL, ... )
X | Regression specification matrix. |
---|---|
y | Column of response variable. |
weights | vector of same length and order as dependent column, to be used as weights for estimation (note, if draw weights is set to TRUE, this variable will be the element-wise product of itself and a random vector of weights) |
sampling_method | One of "leaveRows", "subsampleRows", or "bootstrapRows". |
alpha | Quantiles to be estimated. |
jstar | First quantile to be estimated (usually the center one) |
control | control parameters to pass to the control arguments of
|
algorithm | function which is actually used to fit each quantile regression |
draw_weights | Whether to use random exponential weights for bootstrap, either TRUE or FALSE |
var_names | RHS regression variable names. |
subsample_percent | A number between 0 and one, specifying the percent of the data to subsample for standard error calculations |
... | other arguments passed to quantile fitting function |
cluster_matrix | Matrix of cluster variables, as returned by a model formula |
std_err_control | control parameters to pass to the control arguments of
|
parallel | whether to run in parallel or not |
seed | Seed to be used when generating RNG |