All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
I am pleased to inform you that the current version of your manuscript has been accepted to publish by PeerJ.
[# PeerJ Staff Note - this decision was reviewed and approved by Jörg Oehlmann, a PeerJ Section Editor covering this Section #]
Your manuscript still needs minor changes before it can be officially accepted for publication.
No comment
No comment
In my previous review, I wrote: My sole major concern is that the authors’ Monte-Carlo simulations were made for the delta log-normal. The authors find good performance with the equal-tailed Bayesian based on the independent Jeffreys prior (Figures 1-4). For that analysis type, please add additional simulation with small discrepancy to the probability distribution and evaluate coverage under such conditions.
The authors added sigma^2 = 0.1 to Table 1 and Table 2. This was the addition of small variances. That is not what I requested. The problem is that the authors assumed delta log-normal and then did simulations with delta log-normal. Figure 2 are important but not persuasive. To simulate "discrepancy to the probability distribution" please generate delta log-normal as currently, and then add additional noise additive (mean 0) or multiplicative (mean 1), as the authors think best, and assure that the coverage performance shown in Tables 1 and 2 do not deteriorate substantially.
No comment
All my concerns are corrected.
-
-
-
We now have received three review reports on your manuscript. I have considered them, and based on the advice from the reviewers I think that your manuscript needs major revision according to the review comments. In particular, you should pay more attention to the comments from reviewer 2 while revising your manuscript.
Minor. Lines 15, 43, etc., describe rainfall as following a delta lognormal distribution. The authors consider daily rainfall. Add “daily” throughout (e.g., replacement at line 81).
No comment
My sole major concern is that the authors’ Monte-Carlo simulations were made for the delta log-normal. The authors find good performance with the equal-tailed Bayesian based on the independent Jeffreys prior (Figures 1-4). For that analysis type, please add additional simulation with small discrepancy to the probability distribution and evaluate coverage under such conditions.
No comment
The paper investigates the estimations for the common coefficient of variation of delta-lognormal distributions. The Bayesian parametric estimators are derived. They compare the new estimator with three existing estimators by using simulations and real data(rainfall data in Thailand) analysis. The results show that the equal-tailed Bayesian based on the independent Jeffreys prior was suitable.
It is interesting to give the Bayesian confidence intervals for the common coefficient of variation of delta-lognormal distributions. The results are reasonable and correct.
no comment
The emphasis of this article is not confirmed,It should be an applied one, just from the title.In this case,It should start with the actual issue(rainfall data) to illustrate the importance of interval estimation.From the existing literature,the rainfall data follow the delta-lognormal distribution,while, the existing confirm interval estimates are not available based on this data,it necessary to study the estimation based on the Lognormal distribution.Then,the next issue is the difficulty of direct estimation?The reason to take Bayes? At last,conclusion with estimate data from simulation & data. The reasonable illustrate of the research methodologies is not available,just copy & paste.
The paper is interesting. However, the motivation should be given for more details and discussion section must be provided.
See the attached file
The methods used in this work is quite similar to the paper of the authors published in PeerJ in 2019. This work uses population group k > 2.
Please see the attached file
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.