Description Usage Arguments Value See Also
View source: R/functions_impute.R
Our method involves imputing missing values using both SOC2 and SOC3 smart guessed data as the initial prediction (Iteration 0). These two models' results are then blended using the convergence and blending information calculated from the k-folds cross validation stage of the analysis. These blended results constitute the final imputations for the missing values.
1 2 3 4 5 6 7 8 9 10 | blendImputations(
model.results.soc2,
model.results.soc3,
conv.iter.soc2,
conv.iter.soc3,
soc2.prop,
soc3.prop,
ors.data.sims,
write.files = FALSE
)
|
model.results.soc2 |
Results of iterative modeling, usually from SOC2
smart guessed data (output of |
model.results.soc3 |
Results of iterative modeling, usually from SOC3
smart guessed data (output of |
conv.iter.soc2 |
Convergence iteration of model.results.soc2 (calculated
by |
conv.iter.soc3 |
Convergence iteration of model.results.soc3 (calculated
by |
soc2.prop |
Contribution of model.results.soc2 to blending (calculated
by |
soc3.prop |
Contribution of model.results.soc3 to blending (calculated
by |
ors.data.sims |
Original data augmented with relevant predictors, i.e.
all records, including both known and missing estimates, as well as simulated
data (output of |
write.files |
Should results be written to .csv and .Rdata files; default is FALSE (do not write files) |
Data frame containing all predictors for each observation, along with blended results, i.e. simulated values for known estimates, weighted average of predicted values from each simulation at the specified iterations for missing estimates, and a mean value calculated across all simulations (for known estimates, this is simply the actual value)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.