Modifies a proportional hazards model fitted by `RPHFIT`

(R.W. Payne).

### Options

`PRINT` = string tokens |
Controls printed output (`model` , `deviance` , `summary` , `estimates` , `correlations` , `fittedvalues` , `accumulated` , `monitoring` , `loglikelihood` ); default `mode` , `summ` , `esti` |
---|---|

`METHOD` = string token |
How to change the model (`add` , `drop` , `switch` ); default `add` |

`POOL` = string token |
Whether to pool terms in the accumulated summary generated by the fit |

### Parameter

`TERMS` = formula |
Model specifying the change |
---|

### Description

This procedure allows you to modify the contents of a proportional hazards model that has been fitted by procedure `RPHFIT`

. The change to the model is specified by the `TERMS`

parameter. The setting of the `METHOD`

option specifies how the model is to be changed:

`add` |
adds the terms specified by the `TERMS` parameter to the fitted model; |
---|---|

`drop` |
drops those terms from the fitted model; and |

`switch` |
drops any terms specified by the `TERMS` parameter that are already in the fitted model, and adds those that are not (i.e. this operates similarly to the `SWITCH` directive). |

The default is `METHOD=add`

. Note, though, that any term that is to be added must have been included in the full model specified by the `MAXIMALMODEL`

option of `RPHFIT`

. By default the changes are made individually, one term at a time, so that each one will have its own line in an accumulated analysis of deviance. However, you can set option `POOL=yes`

to make them all at once.

The `PRINT`

option controls printed output with similar settings to those of the `FIT`

directive, except that there is an extra setting `loglikelihood`

to print -2 times the log-likelihood and the number of degrees of freedom in the model after the change. The deviance produced for the terms in the regression model can be assessed using chi-square distributions as usual, but the residual deviance is not usable as the maximal model assumed by the generalized linear models method is inappropriate. So, the residual line is suppressed in the summary and accumulated analysis of deviance.

Options: `PRINT`

, `METHOD`

, `POOL`

.

Parameter: `TERMS`

.

### Method

Further details of the method used here (and by `RPHFIT`

) can be found in Aitkin *et al*. (1989).

### Action with `RESTRICT`

None of the vectors must be restricted (and any restrictions will have been cancelled by `RPHFIT`

).

### Reference

Aitkin, M., Anderson, A., Francis, B. & Hinde, J. (1989). *Statistical Modelling in GLIM*. Oxford University Press.

### See also

Procedures: `KAPLANMEIER`

, `RLIFETABLE`

, `RPHFIT`

, `RPHDISPLAY`

, `RPHKEEP`

, `RPROPORTIONAL`

, `RSTEST`

, `RSURVIVAL`

.

Commands for: Survival analysis.

### Example

CAPTION 'RPHCHANGE example',\ 'Data from Gehan (1965, Biometrika, 52, 203-223).';\ STYLE=meta,plain VARIATE [VALUES=1,1,2,2,3,4,4,5,5,8,8,8,8,11,11,12,12,15,17,22,23,\ 6,6,6,6,7,9,10,10,11,13,16,17,19,20,22,23,25,32,32,34,35] Time & [VALUES=24(0),1,0,1,0,1,1,0,0,1,1,1,0,0,1,1,1,1,1] Censor FACTOR [LABELS=!t(control,'6-mercaptopurine'); VALUES=21(1,2)] Treat FACTOR [LEVELS=42; VALUES=1...42] Subject RPHFIT [TIMES=Time; SUBJECTS=Subject; CENSORED=Censor; MAXIMAL=Treat] RPHCHANGE Treat