Confidence Intervals for Functions of Log-Normal Parameters Under Copula Dependence Structures: Applications to Tornado Damage Areas in Canada

The log-normal distribution is a commonly used parametric distribution applied in reliability and survival analysis. For two or more populations, various techniques have been developed to derive confidence intervals for functions of the population parameters under the assumptions of independence and linear dependence between the samples. We extend the existing log-normal confidence interval methodologies by utilizing a jackknifing procedure based on the inference for margins methodology under parametrically defined copula dependence structures. We assess the performance of the procedure on simulated data and apply the methodology to calculate confidence intervals for the mean maximal damage area caused by ground based tornadoes in Canada.