A family of lifetime distributions is considered. Two measures of reliability are considered, R(t) = P(X > t) and P = P(X > Y). Point estimation and testing procedures are developed for R(t) and P based on records. Two types of point estimators are developed—uniformly minimum variance unbiased estimators and maximum likelihood estimators. A comparative study of different methods of estimation is done through simulation studies. Testing procedures are developed for the hypothesis related to different parametric functions.