In the counting process formulation, data for each subject are identified by a triple of counting, atrisk, and covariate processes. Here, indicates the number of events that the subject experiences over the time interval ; indicates whether the subject is at risk at time t (one if at risk and zero otherwise); and is a vector of explanatory variables for the subject at time t. The sample path of N is a step function with jumps of size +1 at the event times, and . Unless changes continuously with time, the data for each subject can be represented by multiple observations, each identifying a semiclosed time interval , the values of the explanatory variables over that interval, and the event status at . The subject remains at risk during the interval , and an event might occur at . Values of the explanatory variables for the subject remain unchanged in the interval. This style of data input was originated by Therneau (1994).
For example, a patient has a tumor recurrence at weeks 3, 10, and 15 and is followed up to week 23. Consider three fixed explanatory
variables Trt
(treatment), Number
(initial tumor number), and Size
(initial tumor size), and one timedependent covariate Z
that represents a hormone level. The value of Z might change during the followup period. The data for this patient are represented
by the following four observations:








0 
3 
1 
1 
1 
3 
12.3 
3 
10 
1 
1 
1 
3 
14.7 
10 
15 
1 
1 
1 
3 
13.8 
15 
23 
0 
1 
1 
3 
15.5 
Here (T1
,T2
] contains the atrisk intervals. The variable Status
indicates whether a recurrence has occurred at T2
; a value of 1 indicates a tumor recurrence, and a value of 0 indicates nonrecurrence. The following statements fit a multiplicative
hazards model with baseline covariates Trt
, Number
, and Size
, and a timevarying covariate Z
.
proc phreg; model (T1,T2) * Status(0) = Trt Number Size Z; run;
Another useful application of the counting process formulation is delayed entry of subjects into the risk set. For example,
in studying the mortality of workers exposed to a carcinogen, the survival time is chosen to be the worker’s age at death
by malignant neoplasm. Any worker joining the workplace at a later age than a given event failure time is not included in
the corresponding risk set. The variables of a worker consist of Entry
(age at which the worker entered the workplace), Age
(age at death or age censored), Status
(an indicator of whether the observation time is censored, with the value 0 identifying a censored time), and X1
and X2
(explanatory variables thought to be related to survival). The specification for such an application is as follows:
proc phreg; model (Entry, Age) * Status(0) = X1 X2; run;
Alternatively, you can use a timedependent variable to control the risk set, as illustrated in the following specification:
proc phreg; model Age * Status(0) = X1 X2; if Age < Entry then X1= .; run;
Here, X1
becomes a timedependent variable. At a given death time t, the value of X1
is reevaluated for each subject with Age
; subjects with Entry
are given a missing value in X1
and are subsequently removed from the risk set. Computationally, this approach is not as efficient as the one that uses the
counting process formulation.