View source: R/bootstrap_summaries_helpers.R
| summarize_bootstrap_events | R Documentation |
Provides summary statistics for event counts across bootstrap iterations, helping assess the reliability of HR estimates when events are sparse.
summarize_bootstrap_events(boot_results, threshold = 5)
boot_results |
List. Output from forestsearch_bootstrap_dofuture() |
threshold |
Integer. Minimum event threshold for flagging low counts (default: 5) |
This function summarizes event counts in four scenarios:
ORIGINAL subgroup H evaluated on BOOTSTRAP samples
ORIGINAL subgroup Hc evaluated on BOOTSTRAP samples
NEW subgroup H* (found in bootstrap) evaluated on ORIGINAL data
NEW subgroup Hc* (found in bootstrap) evaluated on ORIGINAL data
Low event counts (below threshold) can lead to unstable HR estimates. This summary helps identify potential issues with sparse events.
Invisibly returns a list with summary statistics:
The event threshold used
Total number of bootstrap iterations
Number of iterations that found a new subgroup
List with low event counts for original H on bootstrap samples
List with low event counts for original Hc on bootstrap samples
List with low event counts for new H* on original data
List with low event counts for new Hc* on original data
## Not run:
# After running bootstrap analysis
summarize_bootstrap_events(fs_bc, threshold = 10)
## End(Not run)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.