Here I have attached disturbance estimates (sum of disturbance in each plot) of randomly selected plots. The zero values indicates no disturbance, means no disturbance had observed in those sample plots. The data violate assumption of normality even performing various transformations due to values with zero inflation (no disturbance). The objective is to derive a statistically sound estimator (+ confidence interval) of disturbance parameter. I was thinking to conduct a nonparametric analysis for uncertainty estimate of median (emissions) along with additional analysis – such as bootstrapping to generate alternate uncertainty estimate, as a part of validation of nonparametric (percentile) CI estimate. Would be interested to get your thoughts on this. Please do let me know if you need further clarification on the problem. I am using STATA 15.1.