You can use survival probabilities in nonparametric distribution analysis (right censoring) with the Kaplan-Meier estimates to calculate the median, the first quartile (Q1), and the third quartile (Q3):
- The median is the time associated with the first survival probability in the table less than or equal to 0.50.
- Q1 is the time associated with the first survival probability in the table less than or equal to 0.75.
- Q3 is the time associated with the first survival probability in the table less than or equal to 0.25.
For example, suppose you have the following output:
Distribution Analysis: Temp100
Variable: Temp100
Censoring
Censoring Information Count
Uncensored value 34
Right censored value 6
Censoring value: Cens100 = 0
Nonparametric Estimates
Characteristics of Variable
Standard 95.0% Normal CI
Mean(MTTF) Error Lower Upper Q1 Median Q3 IQR
44.7813 4.43366 36.0914 53.4711 24 38 54 30
- Median = 38
- The first survival probability in the table that is less than or equal to 0.50 is 0.475. The time associated with this survival probability is 38; therefore, the median is 38.
- Q1 = 24
- The first survival probability in the table that is less than or equal to 0.75 is 0.75. The time associated with this survival probability is 24; therefore, Q1 is 24.
- Q3 = 54
- The first survival probability in the table that is less than or equal to 0.25 is 0.25. The time associated with this survival probability is 54; therefore, Q3 is 54.
If the survival probability cannot be found in the table, then the quartile or median value is displayed as an *. For example, in the following table, there is no survival probability less than or equal to 0.25, so Q3 is *.
Distribution Analysis: Temp80
Variable: Temp80
Censoring
Censoring Information Count
Uncensored value 37
Right censored value 13
Censoring value: Cens80 = 0
Nonparametric Estimates
Characteristics of Variable
Standard 95.0% Normal CI
Mean(MTTF) Error Lower Upper Q1 Median Q3 IQR
63.7123 3.83453 56.1968 71.2279 48 55 * *
