I encountered an unusual observation while constructing a nomogram using the rms package with the Cox proportional hazards model. Specifically, when Karnofsky Performance Status (KPS) is used as a alone predictor, the nomogram points for KPS decrease from high to low. However, when KPS is combined with other variables in a multivariable model, the points for KPS increase from low to high. Additionally, I've noticed that the total points vary from low to high for all variables, while the 1-year survival probability shifts from high to low.
Could anyone help clarify why this directional shift in points occurs? Are there known factors, such as interactions, scaling differences, or confounding effects, that might explain this pattern?
Dear Harpreet,
A directional shift in KPS nomogram points between univariate and multivariable Cox models (in rms) occurs due to confounding. In the multivariable model, KPS’s effect is adjusted alongside other factors, which can reveal hidden interactions or change its apparent impact on survival.Hope this answers your requirement
- Badges
- Science topic
- Similar topics
- Chemistry
- Pharmacology
- Medical Pharmacology
- Clinical Pharmacology