Generalized linear models for analyzing count data of rainfall occurrences

Author:

Sumi Sharmin Nahar,Sinha Narayan ChandraORCID,Islam M. Ataharul

Abstract

AbstractHaving the adequate knowledge about the behavior of climatic variables on the occurrences of rainfall is needed to the country’s economists and agriculturists for saving the country’s people from the devastating natural hazards like flash flood, drought, heavy rainfall, etc. Therefore, the study has been taken initiative to identify the influence of climatic variables for the occurrences of rainfall. The study has been developed generalized linear models (GLMs) for Poisson distribution for weekly and fortnightly count data of daily rainfall occurrences for the summer and monsoon seasons for five regional rainfall stations of Bangladesh. For these models, minimum and maximum temperatures and relative humidity are considered as explanatory variables. For five regional rainfall stations, the model selection procedures AIC and BIC indicate that the GLMs for the Poisson distribution satisfactorily explain the influence of climatic variables for the fortnightly occurrences of rainfall in the summer and monsoon seasons. The GLMs for the summer season of fortnightly occurrences of rainfall indicate that if one unit of relative humidity increases, then the probability of rainy days will be increased by 12 percent in Feni station, 6 percent in Sylhet, Khulna and Rajshahi stations, and 7 percent in Dhaka station. Besides, the GLMs for the monsoon season of fortnightly occurrences of rainfall indicate that if one unit increases of minimum temperature, then the probability of rainy days will be increased by 22 percent, 19 percent, 24 percent, 17 percent and 19 percent in Feni, Sylhet, Khulna, Rajshahi and Dhaka stations, respectively. Further, maximum temperature indicates negative influence on the occurrences of rainfall for all the stations and seasons of the period. The study indicates that the relative humidity for summer season and minimum temperature for monsoon season play remarkable role for changing fortnightly occurrences of rainfall in all the regions of the country.

Publisher

Springer Science and Business Media LLC

Subject

General Earth and Planetary Sciences,General Physics and Astronomy,General Engineering,General Environmental Science,General Materials Science,General Chemical Engineering

Reference49 articles.

1. Agresti A (1984) Analysis of ordinal categorical data. Wiley, New York

2. Ahasan MN, Chowdhary AM, Quadir DA (2010) Variability and trends of summer monsoon rainfall over Bangladesh. J Hydrol Meteorol 7(1):1–17. https://doi.org/10.3126/jhm.v7i1.5612

3. Akaike H (1974) A new look at the statistical identification model. IEEE Trans Autom Control 19(6):716–723. https://doi.org/10.1109/TAC.1974.1100705

4. Akaike H (1972) Use of information theoretic quantify for statistical model identification. In: Proceedings of the 5th Hawaii international conference system sciences, Western Periodicals, pp 249–250.

5. Akaike H (1972) Information theory and an extension of the maximum likelihood principle. In: Petrov BN, Csaki F (eds) Second international symposium on information theory. Aka-demiai Kiado, Budapest, pp 267–281

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3