logistf.control: Control Parameters for 'logistf'

Description Usage Arguments Details Value Author(s) Examples

View source: R/logistf.control.R

Description

Sets parameters for Newton-Raphson iteration in Firth's penalized-likelihood logistic regression

Usage

1
2
logistf.control(maxit = 25, maxhs = 5, maxstep = 5, lconv = 1e-05, gconv = 1e-05, 
    xconv = 1e-05, collapse=TRUE)

Arguments

maxit

the maximum number of iterations

maxhs

the maximum number of step-halvings in one iteration. The increment of the beta vector within one iteration is divided by 2 if the new beta leads to a decrease in log likelihood.

maxstep

specifies the maximum step size in the beta vector within one iteration.

lconv

specifies the convergence criterion for the log likelihood.

gconv

specifies the convergence criterion for the first derivative of the log likelihood (the score vector).

xconv

specifies the convergence criterion for the parameter estimates.

collapse

if TRUE, evaluates all unique combinations of x and y and collapses data set. This may save computing time with large data sets with only categorical (binary) covariates.

Details

logistf.control() is used by logistf and logistftest to set control parameters to default values. Different values can be specified, e. g., by logistf(..., control= logistf.control(maxstep=1)).

Value

maxit

the maximum number of iterations

maxhs

the maximum number of step-halvings in one iteration. The increment of the beta vector within one iteration is divided by 2 if the new beta leads to a decrease in log likelihood.

maxstep

specifies the maximum step size in the beta vector within one iteration.

lconv

specifies the convergence criterion for the log likelihood.

gconv

specifies the convergence criterion for the first derivative of the log likelihood (the score vector).

xconv

specifies the convergence criterion for the parameter estimates.

collapse

if TRUE, evaluates all unique combinations of x and y and collapses data set.

Author(s)

Georg Heinze

Examples

1
2
3
4
data(sexagg)
fit2<-logistf(case ~ age+oc+vic+vicl+vis+dia, data=sexagg, weights=COUNT, 
   control=logistf.control(maxstep=1))
summary(fit2)

Example output

logistf(formula = case ~ age + oc + vic + vicl + vis + dia, data = sexagg, 
    control = logistf.control(maxstep = 1), weights = COUNT)

Model fitted by Penalized ML
Confidence intervals and p-values by Profile Likelihood Profile Likelihood Profile Likelihood Profile Likelihood Profile Likelihood Profile Likelihood Profile Likelihood 

                   coef  se(coef) lower 0.95  upper 0.95       Chisq
(Intercept)  0.12025405 0.4855415 -0.8185574  1.07315110  0.06286298
age         -1.10598130 0.4236601 -1.9737884 -0.30742658  7.50773092
oc          -0.06881673 0.4437934 -0.9414360  0.78920042  0.02467044
vic          2.26887464 0.5484160  1.2730233  3.43543174 22.93139022
vicl        -2.11140816 0.5430824 -3.2608608 -1.11773667 19.10407252
vis         -0.78831695 0.4173676 -1.6080879  0.01518319  3.69740975
dia          3.09601259 1.6750089  0.7745730  8.03028804  7.89693139
                       p
(Intercept) 8.020268e-01
age         6.143472e-03
oc          8.751911e-01
vic         1.678877e-06
vicl        1.237805e-05
vis         5.449701e-02
dia         4.951873e-03

Likelihood ratio test=49.09064 on 6 df, p=7.15089e-09, n=239
Wald test = 30.64066 on 6 df, p = 2.968387e-05

Covariance-Matrix:
            [,1]          [,2]         [,3]        [,4]         [,5]
[1,]  0.23575055 -0.0274268365 -0.195208806 -0.12109972 -0.028931309
[2,] -0.02742684  0.1794879046  0.001817983 -0.02316594  0.034595748
[3,] -0.19520881  0.0018179831  0.196952622  0.08788776  0.025843013
[4,] -0.12109972 -0.0231659370  0.087887763  0.30076006 -0.195031761
[5,] -0.02893131  0.0345957476  0.025843013 -0.19503176  0.294938443
[6,] -0.04648041  0.0007176955  0.042053108 -0.01532464 -0.047269900
[7,] -0.02697950 -0.0655714667  0.025480404  0.02521145 -0.008037389
              [,6]         [,7]
[1,] -0.0464804061 -0.026979496
[2,]  0.0007176955 -0.065571467
[3,]  0.0420531076  0.025480404
[4,] -0.0153246406  0.025211447
[5,] -0.0472699002 -0.008037389
[6,]  0.1741956847 -0.045265534
[7,] -0.0452655335  2.805654878

logistf documentation built on May 30, 2017, 5:25 a.m.