fit_control • capybara

fit_control {capybara}

R Documentation

Set `feglm` Control Parameters

Description

Set and change parameters used for fitting feglm, felm, and fenegbin. Termination conditions are similar to glm.

Usage

fit_control(
  dev_tol = 1e-08,
  center_tol = 1e-06,
  center_tol_loose = 1e-04,
  collin_tol = 1e-10,
  step_halving_factor = 0.5,
  alpha_tol = 1e-08,
  iter_max = 25L,
  iter_center_max = 10000L,
  iter_inner_max = 50L,
  iter_alpha_max = 10000L,
  step_halving_memory = 0.9,
  max_step_halving = 2L,
  start_inner_tol = 1e-06,
  grand_acc_period = 4L,
  centering = "berge",
  sep_tol = 1e-08,
  sep_zero_tol = 1e-12,
  sep_max_iter = 200L,
  sep_simplex_max_iter = 2000L,
  sep_use_relu = TRUE,
  sep_use_simplex = TRUE,
  return_fe = TRUE,
  keep_tx = FALSE,
  check_separation = TRUE,
  init_theta = 0,
  vcov_type = NULL
)

Arguments

dev_tol tolerance level for the first stopping condition of the maximization routine. The stopping condition is based on the relative change of the deviance in iteration r and can be expressed as follows: |dev_{r} - dev_{r - 1}| / (0.1 + |dev_{r}|) < tol. The default is 1.0e-08.

center_tol tolerance level for the stopping condition of the centering algorithm. The stopping condition is based on the relative change of the centered variable similar to the 'lfe' package. The default is 1.0e-06.

center_tol_loose initial (loose) tolerance for adaptive centering in GLM iterations. During early IRLS iterations when deviance is changing rapidly, this looser tolerance is used to save computation. As the GLM converges, the tolerance is tightened towards center_tol. The default is 1.0e-04.

collin_tol tolerance level for detecting collinearity. The default is 1.0e-07.

step_halving_factor numeric indicating the factor by which the step size is halved to iterate towards convergence. This is used to control the step size during optimization. The default is 0.5.

alpha_tol tolerance for fixed effects (alpha) convergence. The default is 1.0e-06.

iter_max integer indicating the maximum number of iterations in the maximization routine. The default is 25L.

iter_center_max integer indicating the maximum number of iterations in the centering algorithm. The default is 10000L.

iter_inner_max integer indicating the maximum number of iterations in the inner loop of the centering algorithm. The default is 50L.

iter_alpha_max maximum iterations for fixed effects computation. The default is 10000L.

step_halving_memory numeric memory factor for step-halving algorithm. Controls how much of the previous iteration is retained. The default is 0.9.

max_step_halving maximum number of post-convergence step-halving attempts. The default is 2.

start_inner_tol starting tolerance for inner solver iterations. The default is 1.0e-04.

grand_acc_period integer indicating the period (in iterations) for grand acceleration in the centering algorithm. Grand acceleration applies a second-level Irons-Tuck extrapolation on the overall convergence trajectory. Lower values (e.g., 4-10) may speed up convergence for difficult problems. Set to a very large value (e.g., 10000) to effectively disable. The default is 4L.

centering character string indicating the centering algorithm to use for demeaning fixed effects. "stammann" (default) uses alternating projections with Gauss-Seidel sweeps plus Irons-Tuck and grand acceleration on coefficient vectors. Each iteration updates each fixed-effect dimension in sequence. "berge" uses a fixed-point reformulation as described in Berge (2018): all FE updates are composed into a single map F = f_T \circ f_I, reducing the problem to finding \beta^* = F(\beta^*). The Irons and Tuck (1969) acceleration is then applied to the composed iteration. Both methods use warm-starting and grand acceleration.

sep_tol tolerance for separation detection. The default is 1.0e-08.

sep_zero_tol tolerance for treating values as zero in separation detection. The default is 1.0e-12.

sep_max_iter maximum iterations for ReLU separation detection algorithm. The default is 200L.

sep_simplex_max_iter maximum iterations for simplex separation detection algorithm. The default is 2000L.

sep_use_relu logical indicating whether to use the ReLU algorithm for separation detection. The default is TRUE.

sep_use_simplex logical indicating whether to use the simplex algorithm for separation detection. The default is TRUE.

return_fe logical indicating if the fixed effects should be returned. This can be useful when fitting general equilibrium models where skipping the fixed effects for intermediate steps speeds up computation. The default is TRUE and only applies to the feglm class.

keep_tx logical indicating if the centered regressor matrix should be stored. The centered regressor matrix is required for some covariance estimators, bias corrections, and average partial effects. This option saves some computation time at the cost of memory. The default is TRUE.

check_separation logical indicating whether to perform separation detection for Poisson models. When TRUE (default), observations with perfect prediction are automatically detected and excluded from estimation. Set to FALSE to skip this check and speed up computation when separation is known not to be an issue. The default is TRUE.

init_theta Initial value for the negative binomial dispersion parameter (theta). The default is 0.0.

vcov_type Optional character string specifying the type of variance-covariance estimator to be used. It only applies for formulas with a cluster variable like z ~ x + y | fe | cl. When NULL (default), the variance covariance matrix follows a regular sandwich estimator. When set to "m-estimator", uses standard clustered M-estimator sandwich. When set to "m-estimator-dyadic", uses dyadic clustering that accounts for correlation between observations sharing entities. For dyadic clustering, specify two entity columns in the formula like z ~ x + y | fe | cl1 + cl2.

Value

A named list of control parameters.

Examples

fit_control(0.05, 0.05, 10L, 10L, TRUE, TRUE, TRUE)