论文信息 - Estimating the Difference in the Percentiles of Two Delta-Lognormal Independent Populations

Estimating the Difference in the Percentiles of Two Delta-Lognormal Independent Populations

In this study, estimating the difference in the percentiles of two delta-lognormal independent populations was of interest. We used several parameters in a simulation study to compare two delta-lognormal independent populations in terms of percentiles. By simulation, it was found that the coverage probabilities were sufficiently small with a small sample size (\(n = 10\), \(m = 10\) and \(n = 50\), \(m = 10\)), but when the size of the sample was large, the coverage probabilities increased in all three cases in this study. When applying our method to a real-life weather situation, we found that the rainfall data from the Ping River in Northern Thailand (Fang and Chiang Dao, Chiang Mai province) followed delta-lognormal distribution using the confidence interval of delta-lognormal distribution percentiles and that the coverage probability was well estimated.

Suparat Niwitpong | Sa-Aat Niwitpong | Maneerat Jaithun

[1] K. Krishnamoorthy,et al. Confidence intervals for the mean and a percentile based on zero-inflated lognormal data , 2018 .

[2] Romual Eloge Tchouta. Estimating the difference of percentiles from two independent populations , 2008 .

[3] Confidence Intervals for Mean and Difference between Means of Normal Distributions with Unknown Coefficients of Variation , 2017 .

[4] K. Krishnamoorthy,et al. Confidence limits for lognormal percentiles and for lognormal mean based on samples with multiple detection limits. , 2011, The Annals of occupational hygiene.

[5] Suparat Niwitpong,et al. Confidence Intervals for the Ratio of Means of Delta-Lognormal Distribution , 2018, ECONVN.

[6] W. J. Owen,et al. Estimation of the Mean for Lognormal Data Containing Zeroes and Left-Censored Values, with Applications to the Measure- ment of Worker Exposure to Air Contaminants , 1980 .