> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fincept.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Survival and duration analysis

> Time-to-event analysis with censoring: Cox proportional hazards regression with hazard ratios and baseline hazards, Kaplan-Meier survival curves with confidence bands and median survival, log-rank and weighted tests between groups, and cumulative incidence under competing risks.

Toolset `stats_survival`: 4 tools.

| Tool | What it does | Notes |
| - | - | - |
| `stats_cox_ph` | Cox proportional hazards regression for censored durations (time to default, prepayment, delisting, client attrition): how covariates scale the hazard of the event. | |
| `stats_kaplan_meier` | Kaplan-Meier estimate of the survival function from censored durations, overall or per group (fund survival, loan survival to default, client retention). | |
| `stats_logrank_test` | Tests whether survival differs between groups (default timing by rating, fund survival by strategy): the log-rank test or a weighted variant (Gehan-Breslow, Tarone-Ware, Fleming-Harrington), optionally stratified. | |
| `stats_cumulative_incidence` | Cumulative incidence of each cause under competing risks (a mortgage ends in default or prepayment, a fund closes or merges): the probability of having failed from each cause by every time, which, unlike one minus a Kaplan-Meier curve, accounts for the other causes. | |

Inputs, limits and outputs are described in [Fincept Stats](/guides/fincept-stats). Full schemas: `fincept_describe_tool`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.