Hello Readers, I am looking for guidance on calculating degrees of freedom for an external validation of a clinical prediction rule. The calculation for sample size is as follows:
We will include 4,875 patients. The recommended sample size for validation studies is a minimum of 100 events and a minimum of 100 non-events. During derivation, the study team derived an accurate model from a total sample size of 2,399 patients of whom 263 patients suffered adverse events. Thus, we have more than adequate degrees of freedom to validate the model and refine it if needed. Though the minimum is 100 patients with adverse events, a large sample size of 536 patients with adverse events will have adequate precision to estimate the sensitivity of the score using a two-sided 95% CI across all risk categories of interest. The margin of error will be +/- 3.1% for a sensitivity of 85% (CI 81.7% to 87.9%), or an exact binomial CI from 97.7% to 99.7% for a sensitivity of 99%.
I would appreciate it if someone could guide me on how to calculate the degrees of freedom for the above sample size. The derived tool has 7 parameters.