Prints a comprehensive summary of the robust covariance estimation results, including coefficients, robust standard errors, z-statistics, and p-values.
Usage
# S3 method for class 'robcov_vglm'
summary(object, ...)Examples
trial <- sim_markov("actt2", n_patients = 40, follow_up_time = 6, seed = 1)
markov_data <- prepare_markov_data(trial, absorbing_state = 8)
fit <- vglm_markov(
ordered(y) ~ time + tx + yprev,
family = VGAM::cumulative(reverse = TRUE, parallel = TRUE),
data = markov_data
)
#> Warning: `id_var` was not supplied to vglm_markov(); stored patient-ID metadata, cluster-robust standard errors for frequentist wrappers, and automatic FWB refits will not be available from the fitted object.
#> Warning: 12 diagonal elements of the working weights variable 'wz' have been replaced by 1.819e-12
#> Warning: 76 diagonal elements of the working weights variable 'wz' have been replaced by 1.819e-12
#> Warning: 77 diagonal elements of the working weights variable 'wz' have been replaced by 1.819e-12
#> Warning: 128 diagonal elements of the working weights variable 'wz' have been replaced by 1.819e-12
#> Warning: 151 diagonal elements of the working weights variable 'wz' have been replaced by 1.819e-12
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: 151 diagonal elements of the working weights variable 'wz' have been replaced by 1.819e-12
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: 151 diagonal elements of the working weights variable 'wz' have been replaced by 1.819e-12
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: 151 diagonal elements of the working weights variable 'wz' have been replaced by 1.819e-12
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: fitted values close to 0 or 1
#> Warning: It seems that the nonparallelism assumption has resulted in intersecting linear/additive predictors. Try propodds() or fitting a partial nonproportional odds model or choosing some other link function, etc.
#> Warning: some quantities such as z, residuals, SEs may be inaccurate due to convergence at a half-step
robust_fit <- robcov_vglm(fit, cluster = markov_data$id)
summary(robust_fit)
#> Robust (Sandwich) Covariance Estimation for vglm
#> ================================================
#>
#> Call:
#> vglm_markov(formula = ordered(y) ~ time + tx + yprev, family = VGAM::cumulative(reverse = TRUE,
#> parallel = TRUE), data = markov_data)
#>
#> Number of observations: 240
#> Bread: observed
#> HC type: HC0
#> Number of clusters: 40
#> Cluster adjustment: applied (n/(n-1))
#> Combined adjustment factor: 1.02564
#>
#> Coefficients (Robust SE):
#> Estimate Std. Error z value Pr(>|z|)
#> (Intercept):1 -0.2507 0.8256 -0.3037 7.613e-01
#> (Intercept):2 -21.5700 2.0097 -10.7331 7.120e-27 ***
#> (Intercept):3 -21.8089 2.0984 -10.3929 2.671e-25 ***
#> (Intercept):4 -24.2886 1.9613 -12.3841 3.186e-35 ***
#> (Intercept):5 -28.7620 1.9839 -14.4979 1.248e-47 ***
#> (Intercept):6 -33.3092 2.0652 -16.1291 1.593e-58 ***
#> time -0.2626 0.1112 -2.3619 1.818e-02 *
#> tx -0.1648 0.3198 -0.5153 6.063e-01
#> yprev2 -0.8884 0.8756 -1.0146 3.103e-01
#> yprev3 11.8641 0.9312 12.7405 3.521e-37 ***
#> yprev4 23.9845 1.8741 12.7978 1.687e-37 ***
#> yprev5 26.5162 1.7749 14.9395 1.822e-50 ***
#> yprev6 32.2501 1.8908 17.0563 3.138e-65 ***
#> yprev7 37.2190 2.0378 18.2645 1.586e-74 ***
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#>
#> Model fit:
#> deviance: 306
#> loglikelihood: -153
#>