feglm Control ParametersSet and change parameters used for fitting feglm.
Termination conditions are similar to glm.
fit_control(
dev_tol = 1e-08,
center_tol = 1e-08,
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,
iter_interrupt = 1000L,
iter_ssr = 10L,
step_halving_memory = 0.9,
max_step_halving = 2L,
start_inner_tol = 1e-06,
accel_start = 6L,
project_tol_factor = 0.001,
grand_accel_tol = 1e-10,
project_group_tol = 1e-12,
irons_tuck_tol = 1e-10,
grand_accel_interval = 5L,
irons_tuck_interval = 3L,
ssr_check_interval = 40L,
convergence_factor = 1.1,
tol_multiplier = 20,
return_fe = TRUE,
keep_tx = FALSE,
init_theta = 0
)A named list of control parameters.
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.
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-08.
tolerance level for detecting collinearity. The default is
1.0e-07.
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.
tolerance for fixed effects (alpha) convergence.
The default is 1.0e-06.
unsigned integer indicating the maximum number of iterations
in the maximization routine. The default is 25L.
unsigned integer indicating the maximum number of
iterations in the centering algorithm. The default is 10000L.
unsigned integer indicating the maximum number of
iterations in the inner loop of the centering algorithm. The default is
50L.
maximum iterations for fixed effects computation.
The default is 10000L.
unsigned integer indicating the maximum number of
iterations before the algorithm is interrupted. The default is 1000L.
unsigned integer indicating the number of iterations
to skip before checking if the sum of squared residuals improves. The default
is 10L.
numeric memory factor for step-halving algorithm.
Controls how much of the previous iteration is retained. The default is 0.9.
maximum number of post-convergence step-halving attempts.
The default is 2.
starting tolerance for inner solver iterations.
The default is 1.0e-04.
Integer. Iteration to start conjugate gradient acceleration in centering.
The default is 6L.
Factor to multiply center_tol for projection tolerance.
The default is 1e-3.
Tolerance for grand acceleration convergence.
The default is 1e-10.
Tolerance for individual group projections.
The default is 1e-12.
Tolerance for Irons-Tuck acceleration.
The default is 1e-10.
Interval for applying grand acceleration.
The default is 5L.
Interval for applying Irons-Tuck acceleration.
The default is 3L.
Interval for adaptive SSR convergence checks.
The default is 40L.
Factor for detecting slow convergence.
The default is 1.1.
Multiplier for early termination tolerance check.
The default is 20.0.
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.
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.
Initial value for the negative binomial dispersion parameter (theta).
The default is 0.0.
feglm
fit_control(0.05, 0.05, 10L, 10L, TRUE, TRUE, TRUE)
Run the code above in your browser using DataLab