The model can be expressed as h(t) = h 0 t)exp(β 1 x 1 + β 2 x 2 + … + β k x k) or equally as ln[h(t)] = ln[h 0 t)] + β 1 x 1 + β 2 x 2 + … + β k x k, in which h(t) is the hazard rate for failure over the time t and h 0 t) is the baseline hazard rate17.
The longer the patient remained on first-line cART, the lower was the hazard for second-line failure, with a 3% decrease in the hazard of failure for each additional month on first line cART.
Whilst not significant, a higher hazard of failure was observed for patients initiating second-line with an HIV RNA level between 10,001-100,000 copies/ml, when compared to those with HIV RNA levels <10,000 copies/ml (p = 0.06).
The hazard of failure at time t for patient i is modelled as where h0 t) is either a parametric or semi-parametric baseline hazard function, α is a parameter measuring the association between the observed longitudinal measurement and the hazard of failure at time t, and x i is a vector of further explanatory variables with regression parameters β.
The association of various factors with the hazards of failure for the time-to-endpoint PFS was estimated using the Cox proportional hazard regression model.
Specific inclusion/exclusion criteria are shown in table 3. We used Cox-proportional hazards models to investigate risk factors for failure secondary to ARMD following the hip resurfacing procedure.
For the prospective cohort analyses, we will use Cox proportional hazards models for failure-time data, using SAS PROC PHREG, to estimate relative risks and 95% CIs associated with the various exposures, as this allows for multivariate adjustment and evaluation of interactions [ 51].
We fitted a Cox proportional hazards model to assess the risk factors for failure or subsequent glaucoma surgery in that eye.
The Cox models showed that larger centre volumes reduced the cs-hazard for technique failure, but did not change the cs-hazards for death or transplantation.
The pattern of sex differences was less pronounced for first manifestations of cerebrovascular disease based on the hazard ratios compared with lifetime risks, while the sex difference in hazards for heart failure even reversed in the adjusted models.
