Survival data is a special type of data, which especially is characterised by the occurrence of censored data. The censoring mechanism means that standard statistically methods often are not suitable for analysing this type of data. Instead a range of statistical methods are developed to handle this type of data. A prominent role is played by the Cox proportional hazards model. This model is a regression model used to relate a set of covariates to the hazard function. In this project a new method for analysing survival data is studied. The method is based on pseudo-observations known from the jackknife theory. Pseudo-observations address one of the main problem with survival data, i.e. not having appropriate observations for all individual in the study population. The pseudo-observation approach allows for analysis of survival data by standard statistically methods. In this project the potential and efficiency of pseudo-observations for regression analysis of survival data is considered. Further, the method is compared to the traditional Cox proportional hazards model.