What’s remarkable about partial likelihood is that you can estimate the β coefficients of the proportional hazards model without having to specify the baseline hazard function λ0(t). In this section, we will
consider some general properties of partial likelihood
look at two simple examples using PROC PHREG
examine the mathematics of the method in some detail.
The likelihood function for the proportional hazards model of equation (5.1) can be factored into two parts:
one part depends on both λ0(t) and β (the vector of coefficients)
the other part depends on β alone.
What partial likelihood does, in effect, is discard the first part and treat the second part—the partial likelihood function—as though it were an ordinary likelihood ...