Saddlepoint Approximations for Linear Rank Models

Test statistics from the weighted log-rank class are commonly used to compare treatments when there is right censoring, testing for trend and testing for independence . This thesis uses saddlepoint methods to determine mid-p-values, and confidence intervals from the null permutation distributions of tests from the weighted log-rank class. Analytical saddlepoint computations replace the permutation simulations and provide mid-p-values that are virtually exact for all practical purposes.