Use Parametric Distribution Analysis (Right Censoring) to estimate the overall reliability of your system when your data follow a parametric distribution and contain exact failure times and/or right-censored observations. When data are right-censored, failures are recorded only if they occur before a particular time. A unit surviving longer than that time is considered a right-censored observation. For more information, go to Data censoring.

You can select from 11 distributions to model your lifetime data: smallest extreme value, Weibull, 3-parameter Weibull, exponential, 2-parameter exponential, normal, lognormal, 3-parameter lognormal, logistic, loglogistic, and 3-parameter loglogistic. Based on the fitted distribution, you can do the following:

- Display parameter estimates and distribution characteristics, such as mean time to failure (MTTF)
- Estimate percentiles, survival probabilities, cumulative failure probabilities, and their confidence intervals
- Display survival plots, cumulative failure plots, and hazard plots to graphically analyze the probability of failure or survival
- Assess the fit of the selected distribution with a probability plot

When your product fails in different ways, you can enter failure mode information for this analysis to evaluate the impact of each type of failure on the overall reliability. Each failure mode is assumed to be independent and may be modeled by different distributions. By analyzing each failure mode individually, you can more easily prioritize your improvement efforts.

To perform a parametric distribution analysis for right-censored data, choose

.- If your data include either left-censored observations or interval-censored observations, or have a varied censoring scheme that includes exact failure times, right censoring, left censoring, and/or interval censoring, use Parametric Distribution Analysis (Arbitrary Censoring).
- To determine which parametric distribution best fits your data, use Distribution ID Plot (Right Censoring).
- If no parametric distribution fits your data adequately, use Nonparametric Distribution Analysis (Right Censoring).