Skip to contents

Perturbation family: estimator class

Source: R/estimator.R
stress_estimator.Rd

Refits the question with estimators other than the pre-specified MMRM:

Usage

stress_estimator(
  spec,
  estimators = c("complete_cases", "gee_independence", "ancova", "robust_ancova",
    "random_intercept", "clda"),
  random = NULL,
  baseline = NULL,
  seed = 1,
  cores = 1L,
  diagnostic = NULL
)

Arguments

spec

A stress_spec().

estimators

Which estimators to run.

random

Name of a grouping column for "random_intercept" (a site or centre variable that is also one of the spec's covariates).

baseline

Name of the baseline column for "clda"; the response must be change from that baseline.

seed

Seed for the robust regression's random initial estimate.

cores

Number of worker processes; 1 fits sequentially.

diagnostic

Names of estimators (from estimators) whose rows are diagnostic: fitted, drawn and tabulated with kind = "diagnostic", but not counted by stress_census(), so they do not enter the verdict or its counts. NULL (the default) counts every estimator. The standard plan (standard_plan()) makes the complete-case refit diagnostic.

Value

A stress_rows data frame, one row per estimator.

Details

  • "complete_cases": the pre-specified MMRM on subjects observed at every visit (no reliance on missing-at-random within the likelihood).

  • "gee_independence": working-independence weighted least squares with a visit-specific residual variance and a cluster-robust (sandwich) variance, between-within degrees of freedom; no within-subject covariance is modelled. Needs nlme.

  • "ancova": analysis of covariance at the contrast visit, observed cases, residual degrees of freedom. Covariate terms involving the visit variable are dropped.

  • "robust_ancova": MM-type robust regression at the contrast visit (MASS::rlm), normal-theory inference. Needs MASS.

  • "clda": constrained longitudinal data analysis: the raw outcome (baseline plus the response, which must be a change from baseline) is modelled at baseline and every post-baseline visit with one common baseline mean across arms, an unstructured covariance over all visits and the other covariates as fixed effects; the contrast is the difference in the arms' means at the contrast visit. Needs baseline.

  • "random_intercept": the pre-specified fixed effects with random as a random intercept instead of a fixed covariate, the spec's covariance structure within subject where nlme has an equivalent (us, ar1h, ar1, cs, csh); normal-theory inference. Needs nlme and random.

Every estimator reports the same least-squares-mean contrast at the contrast visit (class covariates at equal weights, continuous covariates at their means).

Examples

spec <- stress_spec(mmrm::fev_data, "FEV1", "USUBJID", "AVISIT", "ARMCD", "PBO",
                    covariates = ~ RACE + SEX + FEV1_BL)
stress_estimator(spec, c("complete_cases", "ancova"))
#>            family                        label        kind        role is_base
#> 1 estimator class       MMRM on complete cases alternative sensitivity   FALSE
#> 2 estimator class ANCOVA at the contrast visit alternative sensitivity   FALSE
#>   converged                                        note estimate   stderr
#> 1      TRUE 39 of 197 subjects observed at all 4 visits  9.42062 3.885616
#> 2      TRUE                 observed cases, residual df  3.89943 1.686347
#>          df      lcl       ucl          p n_subj n_obs     aicc param
#> 1  36.97146 1.547409 17.293831 0.02033658     39   156 983.7926    NA
#> 2 128.00000 0.562705  7.236155 0.02235472    134   134       NA    NA
#>   covariance        method                 vcov           covariates alpha
#> 1         us Kenward-Roger Kenward-Roger-Linear RACE + SEX + FEV1_BL  0.05
#> 2         us      Residual             see note RACE + SEX + FEV1_BL  0.05