cifcurve() | cifplot() | cifpanel() | polyreg()

Default for survival data | Default for competing risks data | Visual elements | Risk ratio label | Panel mode | Zoomed-in-view | Font, style and palette | Axis and label | Proportional hazards check by a log-log plot

Quick start | Why cifmodeling? | Tools for survival and competing risks analysis | Position in the survival ecosystem | Installation | Quality control

Formulas for the Kaplan–Meier estimator | Formulas for the Aalen-Johansen estimator | It is known that the Aalen-Johansen estimator can be expanded under regularity conditions as$$n^{1/2}{\hat F_k(t) - F_k(t)} = n^{-1/2} \sum_{i=1}^n IF_{ik}(t) + o_p(1)$$and the process $n^{1/2}{\hat F_{ik}(t) - F_{ik}(t)}$ converges weakly to a tight Gaussian process. Here $IF_{ik}(t)$ is the influence function, the contribution of $i$-th observation to the Aalen-Johansen estimator, and may be written as$$IF_{ik}(t) =\int_0^t\frac{n S(u^-)}{Y(u)},dM_i(u) | Confidence interval options

Model formula and outcome.type in cifcurve() and polyreg() | Event coding conventions incifmodeling and CDISC ADaM ADTTE | Key arguments of msummary() that are helpful when reporting polyreg() results | Processing pipeline of cifcurve() | Processing pipeline of polyreg() | Reproducibility and conventions for polyreg()

Why direct modeling of CIFs? | Coherent modeling of CIFs using polytomous log odds products | 1. Nuisance model | 2. Effect measures and time points | 3. Censoring adjustment | Estimator and confidence intervals | Return

Example 1. Unadjusted competing risks analysis | Example 2. Survival analysis | Example 3. Adjusted competing risks analysis | Example 4. Description of cumulative incidence of competing events