Calculates the life-table estimate of the survivor function (D.A.Murray).

### Options

`PRINT` = string tokens |
Controls printed output (`lifetable` ); default `life` |
---|---|

`PLOT` = string tokens |
Type of graph to be plotted (`survivor` , `hazard` , `pdf` ); default `surv` , `haza` , `pdf` |

`INTERVAL` = scalar or variate |
A scalar defining the width of the intervals or a variate containing the boundaries of the intervals |

### Parameters

`TIMES` = variates |
Observed timepoints |
---|---|

`CENSORED` = variates |
Variate specifying whether the corresponding element of each `TIMES` variate is censored (1) or represents failures (0) |

`FREQUENCY` = variates |
Variate containing frequencies for the elements of `TIMES` ; by default these are all assumed to be 1 |

`GROUPS` = factors |
Factor specifying the different groups for which to estimate life tables |

`LIFETABLE` = pointers |
Pointer to variates to save the information from each life table |

### Description

`RLIFETABLE`

calculates the life-table estimate, or actuarial estimate, of the survivor function. The life-table method requires a fairly large number of observations so that survival times can be grouped into intervals. These are specified using the `INTERVALS`

option. For equal intervals, you can set `INTERVALS`

to a scalar to define their width. Alternatively you can set `INTERVALS`

to a variate containing the lower boundaries of the intervals. The `PLOT`

option can be used to produce plots of the survivor function (`survivor`

), estimated hazard function (`hazard`

) and the probability density function (`pdf`

). You can set the option `PRINT=*`

to suppress printing of the life table; by default `PRINT=lifetable`

.

The observed timepoints (or the timepoints at which censoring took place) are specified using the `TIMES`

parameter. The `CENSORED`

parameter specifies a variate containing the value one if the corresponding element of `TIMES`

is censored or zero if it was not. `CENSORED`

can be omitted if there was no censoring. If there are several observations (all censored or all uncensored) at a time point, you can specify the time point only once and define the number of observations by specifying a variate of counts using the `FREQUENCY`

parameter. This is particularly useful if the contents of the `TIMES`

variate are intended to identify time intervals rather than discrete time points. The `GROUPS`

parameter can be used to request separate life tables for different groups of data. The `LIFETABLE`

parameter allows the life table to be saved in a pointer to a set of variates for each of the columns within the table.

Options: `PRINT`

, `PLOT`

, `INTERVAL`

.

Parameters: `TIMES`

, `CENSORED`

, `FREQUENCY`

, `GROUPS`

, `LIFETABLE`

.

### Method

The methodology in `RLIFETABLE`

is based on that described in Chapter 4 of Lee (1992).

### Action with `RESTRICT`

The input variates and factors may be restricted identically. The life tables are based only on the units not excluded by the restriction.

### Reference

Lee, E.T. (1992). *Statistical Methods for Survival Data Analysis*. Wiley, New York.

### See also

Procedures: `KAPLANMEIER`

, `RPHFIT`

, `RPROPORTIONAL`

, `RSTEST`

, `RSURVIVAL`

.

Commands for: Survival analysis.

### Example

CAPTION 'RLIFETABLE example',\ !t('Survival data for 2418 male patients with angina pectoris',\ '(Lee 1992, page 91).'); STYLE=meta,plain VARIATE [NVALUES=32] Time; VALUES=!((0.5...15.5)2) & Censor; VALUES=!(16(0,1)) & Count; VALUES=!(456,226,152,171,135,125,83,74,51,42,43,34,18,9,6,0,\ 0,39,22,23,24,107,133,102,68,64,45,53,33,27,23,30) RLIFETABLE [INTERVAL=!(0...15)] Time; CENSORED=Censor; FREQUENCY=Count;\ LIFETABLE=Ltab