Confidence intervals for ratio of means of delta-lognormal distributions based on left-censored data with application to rainfall data in Thailand
PeerJ · 2023
DOI: 10.7717/peerj.16397 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ, 2023. Verfasst von Warisa Thangjai und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, Ramkhamhaeng University, Bangkok, Thailand. Hauptthemen laut MEDLINE: Confidence Intervals. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Office of the Permanent Secretary, Ministry of Higher Education, Science, Research and Innovation (OPS MHESI), Thailand Science Research and Innovation (TSRI)….
Abstract (Originalsprache)
Thailand is a country that is prone to both floods and droughts, and these natural disasters have significant impacts on the country’s people, economy, and environment. Estimating rainfall is an important part of flood and drought prevention. Rainfall data typically contains both zero and positive observations, and the distribution of rainfall often follows the delta-lognormal distribution. However, it is important to note that rainfall data can be censored, meaning that some values may be missing or truncated. The interval estimator for the ratio of means will be useful when comparing the means of two samples. The purpose of this article was to compare the performance of several approaches for statistically analyzing left-censored data. The performance of the confidence intervals was evaluated using the coverage probability and average length, which were assessed through Monte Carlo simulation. The approaches examined included several variations of the generalized confidence interval, the Bayesian, the parametric bootstrap, and the method of variance estimates recovery approaches. For ( ξ 1 , ξ 2 ) = (0.10,0.10), simulations showed that the Bayesian approach would be a suitable choice for constructing the credible interval for the ratio of means of delta-lognormal distributions based on left-censored data. For ( ξ 1 , ξ 2 ) = (0.10,0.25), the parametric bootstrap approach was a strong alternative for constructing the confidence interval. However, the generalized confidence interval approach can be considered to construct the confidence when the sample sizes are increase. Practical applications demonstrating the use of these techniques on rainfall data showed that the confidence interval based on the generalized confidence interval approach covered the ratio of population means and had the smallest length. The proposed approaches’ effectiveness was illustrated using daily rainfall datasets from the provinces of Chiang Rai and Chiang Mai in Thailand.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Statistics, Ramkhamhaeng University, Bangkok, Thailand.
- Department of Applied Statistics, King Mongkut's University of Technology North Bangk, Bangkok, Thailand.
Förderung
- Office of the Permanent Secretary, Ministry of Higher Education, Science, Research and Innovation (OPS MHESI), Thailand Science Research and Innovation (TSRI)…
Zitieren
APA
Thangjai, W., & Niwitpong, S. A. (2023). Confidence intervals for ratio of means of delta-lognormal distributions based on left-censored data with application to rainfall data in Thailand. PeerJ. https://doi.org/10.7717/peerj.16397
Vancouver
Thangjai W, Niwitpong SA. Confidence intervals for ratio of means of delta-lognormal distributions based on left-censored data with application to rainfall data in Thailand. PeerJ. 2023. doi:10.7717/peerj.16397
BibTeX
@article{Thangjai2023,
author = {Thangjai, Warisa and Niwitpong, Sa-Aat},
title = {Confidence intervals for ratio of means of delta-lognormal distributions based on left-censored data with application to rainfall data in Thailand},
journal = {PeerJ},
year = {2023},
doi = {10.7717/peerj.16397}
}
EUVIMED