Number of the records: 1
Nowcasting sunshine number using logistic modeling
- 1.0389974 - ÚI 2014 RIV AT eng J - Journal Article
Brabec, Marek - Badescu, V. - Paulescu, M.
Nowcasting sunshine number using logistic modeling.
Meteorology and Atmospheric Physics. Roč. 120, č. 1-2 (2013), s. 61-71. ISSN 0177-7971. E-ISSN 1436-5065
R&D Projects: GA MŠMT LD12009
Grant - others:European Cooperation in Science and Technology(XE) COST ES1002
Institutional research plan: CEZ:AV0Z1030915
Keywords : logistic regression * Markov model * sunshine number
Subject RIV: BB - Applied Statistics, Operational Research
Impact factor: 1.245, year: 2013
In this paper, we present a formalized approach to statistical modeling of the sunshine number, binary indicator of whether the Sun is covered by clouds introduced previously by Badescu (Theor Appl Climatol 72:127–136, 2002). Our statistical approach is based on Markov chain and logistic regression and yields fully specified probability models that are relatively easily identified (and their unknown parameters estimated) from a set of empirical data (observed sunshine number and sunshine stability number series). We discuss general structure of the model and its advantages, demonstrate its performance on real data and compare its results to classical ARIMA approach as to a competitor. Since the model parameters have clear interpretation, we also illustrate how, e.g., their inter-seasonal stability can be tested. We conclude with an outlook to future developments oriented to construction of models allowing for practically desirable smooth transition between data observed with different frequencies and with a short discussion of technical problems that such a goal brings.
Permanent Link: http://hdl.handle.net/11104/0218865
Number of the records: 1