R/pool_intadj.R
pool_intadj.Rdpool_intadj Provides pooled adjusted intercept after shrinkage of the pooled coefficients
in multiply imputed datasets for models selected with the psfmi_lr function and
internally validated with the psfmi_perform function.
pool_intadj(pobj, shrinkage_factor)An object of class smodsmi (selected models in multiply imputed datasets),
produced by a previous call to psfmi_lr.
A numerical scalar. Shrinkage factor value as a result of internal validation
with the psfmi_perform function.
A pool_intadj object from which the following objects can be extracted: int_adj,
the adjusted intercept value, coef_shrink_pooled, the pooled regression coefficients
after shrinkage, coef_orig_pooled, the (original) pooled regression coefficients before
shrinkage and nimp, the number of imputed datasets.
The function provides the pooled adjusted intercept after shrinkage of pooled regression coefficients in multiply imputed datasets. The function is only available for logistic regression models without random effects.
F. Harrell. Regression Modeling Strategies. With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis (2nd edition). Springer, New York, NY, 2015.
EW. Steyerberg (2019). Clinical Prediction MOdels. A Practical Approach to Development, Validation, and Updating (2nd edition). Springer Nature Switzerland AG.
http://missingdatasolutions.rbind.io/
res_psfmi <- psfmi_lr(data=lbpmilr, nimp=5, impvar="Impnr", Outcome="Chronic",
predictors=c("Gender", "Pain","Tampascale","Smoking","Function",
"Radiation", "Age"), p.crit = 1, method="D1", direction="BW")
res_psfmi$RR_Model
#> NULL
if (FALSE) {
set.seed(100)
res_val <- psfmi_perform(res_psfmi, method = "MI_boot", nboot=10,
int_val = TRUE, p.crit=1, cal.plot=FALSE, plot.indiv=FALSE)
res_val$intval
res <- pool_intadj(res_psfmi, shrinkage_factor = 0.9774058)
res$int_adj
res$coef_shrink_pooled
}