Calibration of direct normal irradiance (DNI) forecasts with quantile regression

2020 ◽  
Author(s):  
Jose L. Casado-Rubio ◽  
Isabel Martínez-Marco ◽  
Carlos Yagüe
Keyword(s):  
Quantile Regression ◽  
Input Parameter ◽  
Training Sample ◽  
Lead Times ◽  
Limited Area ◽  
Continuous Ranked Probability Score ◽  
Direct Normal Irradiance ◽  
High Predictability ◽  
Quantile Regression Method ◽  
Positive Effect

<p>Direct normal irradiance (DNI) forecasts from two ensemble models, the global ECMWF-ENS and the limited area multimodel gSREPS, have been calibrated using the quantile regression method, taking DNI as the only input parameter to better understand the inner workings of the method. Forecasts for the southern part of Spain, with lead times up to 72 hours for ECMWF-ENS and 24 hours for gSREPS over a two-year period (from June 2017 to May 2019), have been used.</p><p>This study has focused on two particular aspects of the postprocess:</p><ul><li>The effect of quantile regression on the spread of the models. The results show that the spread of ECMWF-ENS greatly increases after the postprocess, which has a positive effect on the accuracy of the model, with an improvement of 20% in the continuous ranked probability score (CRPS) after the calibration. However, this increase is uniform over the whole period, affecting equally to situations with low or high spread, hence the postprocessed forecasts are not able to detect changes in predictability. On the other hand raw gSREPS forecasts behave better during episodes of both low or high predictability. The postprocess does not significantly change the spread and accuracy of gSREPS.</li> <li>The influence of the training sample. It has been found that DNI is a variable which can experience periods of low variability, particularly in regions like southern Spain, where long spells of sunny days are common. This has a sizeable impact on the performance of the quantile regression on certain days. Two study cases will be shown to illustrate this problem. Two possible solutions are proposed: use longer training periods (not always possible) or place restrictions on the value of the regression coefficients.</li> </ul>

scholarly journals Pengaruh preferensi sumber pembiayaan dan tingkat pendidikan terhadap pendapatan usaha mikro dan kecil di Indonesia

2021 ◽  
Vol 3 (2) ◽  
pp. 88
Author(s):  
Ramel Yanuarta RE ◽  
Indah Krismanola
Keyword(s):  
Quantile Regression ◽  
Total Sample ◽  
Small Enterprises ◽  
Level Of Education ◽  
Business Units ◽  
Financing Preference ◽  
Micro And Small Enterprises ◽  
The Difference ◽  
Quantile Regression Method ◽  
Positive Effect

This research aims to analyze the effect of financing preference and the level of education of entrepreneurs on quintile of Micro and Small Enterprises (MSEs) revenue in Indonesia. The data used in this research is IFLS data (Indonesian Family Life Survey) waves 4 and 5 with a total sample of 10,336 business units that meet the criteria. Considering the heterogeneous characteristics of the data and the presence of outliers, this study used quantile regression method with a level of confidence (∝=0.05). The results of the analysis show that the education level of entrepreneurs has a positive effect on MSEs revenue and the effect is stronger on the higher MSEs revenue quantile. Meanwhile, the financing preference from own capital generates lower income compared to external or combined sources of financing and the difference is greater in the higher MSEs revenue quintile.Keywords: Micro and small enterprises, level of education, financing preference, quantile regression

scholarly journals Tail-Heaviness, Asymmetry, and Profitability Forecasting by Quantile Regression

2020 ◽  
Author(s):  
Hui Tian ◽  
Andrew Yim ◽  
David P. Newton
Keyword(s):  
Quantile Regression ◽  
Forecast Error ◽  
Simulated Data ◽  
Ordinary Least Squares ◽  
Shape Effect ◽  
Forecasting Accuracy ◽  
Forecasting Performance ◽  
Cash Flow Forecasting ◽  
Positive Effect ◽  
Better Than

We show that quantile regression is better than ordinary-least-squares (OLS) regression in forecasting profitability for a range of profitability measures following the conventional setup of the accounting literature, including the mean absolute forecast error (MAFE) evaluation criterion. Moreover, we perform both a simulated-data and an archival-data analysis to examine how the forecasting performance of quantile regression against OLS changes with the shape of the profitability distribution. Considering the MAFE and mean squared forecast error (MSFE) criteria together, we see that the quantile regression is more accurate relative to OLS when the profitability to be forecast has a heavier-tailed distribution. In addition, the asymmetry of the profitability distribution has either a U-shape or an inverted-U-shape effect on the forecasting accuracy of quantile regression. An application of the distributional shape analysis framework to cash flow forecasting demonstrates the usefulness of the framework beyond profitability forecasting, providing additional empirical evidence on the positive effect of tail-heaviness and supporting the notion of an inverted-U-shape effect of asymmetry. This paper was accepted by Shiva Rajgopal, accounting.

scholarly journals Projection of Long-Term Care Costs in China, 2020–2050: Based on the Bayesian Quantile Regression Method

2019 ◽  
Vol 11 (13) ◽  
pp. 3530 ◽  
Author(s):  
Xiaocang Xu ◽  
Linhong Chen
Keyword(s):  
Quantile Regression ◽  
Long Term Care ◽  
Financial Burden ◽  
Severe Disabilities ◽  
Term Care ◽  
Bayesian Quantile Regression ◽  
The Future ◽  
The Government ◽  
Quantile Regression Method

The aging population in China highlights the significance of elderly long-term care (LTC) services. The number of people aged 65 and above increased from 96 million in 2003 to 150 million in 2016, some of whom were disabled due to chronic diseases or the natural effects of aging on bodily functions. Therefore, the measurement of future LTC costs is of crucial value. Following the basic framework but using different empirical methods from those presented in previous literature, this paper attempts to use the Bayesian quantile regression (BQR) method, which has many advantages over traditional linear regression. Another innovation consists of setting and measuring the high, middle, and low levels of LTC cost prediction for each disability state among the elderly in 2020–2050. Our projections suggest that by 2020, LTC costs will increase to median values of 39.46, 8.98, and 20.25 billion dollars for mild, moderate, and severe disabilities, respectively; these numbers will reach 141.7, 32.28, and 72.78 billion dollars by 2050. The median level of daily life care for mild, moderate, and severe disabilities will increase to 26.23, 6.36, and 27 billion dollars. Our results showed that future LTC cost increases will be enormous, and therefore, the establishment of a reasonable individual-social-government payment mechanism is necessary for the LTC system. The future design of an LTCI system must take into account a variety of factors, including the future elderly population, different care conditions, the financial burden of the government, etc., in order to maintain the sustainable development of the LTC system.

scholarly journals The Impact of Education on Household Income in Rural Vietnam

2020 ◽  
Vol 8 (1) ◽  
pp. 11 ◽  
Author(s):  
Hung Van Vu
Keyword(s):  
Quantile Regression ◽  
Household Income ◽  
Living Standard ◽  
Regression Analyses ◽  
Poor Households ◽  
Quantile Regression Analysis ◽  
Research Findings ◽  
Using Data ◽  
The Impact ◽  
Positive Effect

Using data from the 2018 Vietnam Household Living Standard Survey, our study investigates the impact of education on household income in rural Vietnam. Both mean and quantile regression analyses were employed to analyze the impact of education. We found that education has a positive effect on the household income after controlling for various factors in the models. However, quantile regression analysis reveals that the effect of schooling years increases with quantiles, suggesting that education bring higher returns for richer households. We also found that households with the heads having higher qualifications or vocational education tend to earn higher income levels. Combined together, these findings imply that while education was found to increase household income, it increases income inequality in rural Vietnam. Our research findings suggest that improving the access of poor households to better education is expected to increase their income and reduce inequality in rural Vietnam.

Quantile Regression–Based Estimation of Dynamic Statistical Contingency Fuel

2020 ◽  
Author(s):  
Lei Kang ◽  
Mark Hansen
Keyword(s):  
Quantile Regression ◽  
Traffic Management ◽  
Carbon Dioxide Emission ◽  
Estimation Procedure ◽  
Air Traffic Management ◽  
Aviation Industry ◽  
Fuel Loading ◽  
Data Set ◽  
Fuel Burn ◽  
Quantile Regression Method

Reducing fuel consumption is a unifying goal across the aviation industry. One fuel-saving opportunity for airlines is reducing contingency fuel loading by dispatchers. Many airlines’ flight planning systems (FPSs) provide recommended contingency fuel for dispatchers in the form of statistical contingency fuel (SCF). However, because of limitations of the current SCF estimation procedure, the application of SCF is limited. In this study, we propose to use quantile regression–based machine learning methods to account for fuel burn uncertainties and estimate more reliable SCF values. Utilizing a large fuel burn data set from a major U.S.-based airline, we find that the proposed quantile regression method outperforms the airline’s FPS. The benefit of applying the improved SCF models is estimated to be in the range $19 million–$65 million in fuel expense savings as well as 132 million–451 million kilograms of carbon dioxide emission reductions per year, with the lower savings being realized even while maintaining the current, extremely low risk of tapping the reserve fuel. The proposed models can also be used to predict benefits from reduced fuel loading enabled by increasing system predictability, for example, with improved air traffic management.

scholarly journals Friction Characteristics of Post-Tensioned Tendons of Full-Scale Structures Based on Site Tests

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Haoyun Yuan ◽  
Yuan Li ◽  
Bin Zhou ◽  
Shuanhai He ◽  
Peizhi Wang
Keyword(s):  
Friction Coefficient ◽  
Quantile Regression ◽  
Least Square Method ◽  
Regression Method ◽  
Full Scale ◽  
Least Square ◽  
Friction Characteristics ◽  
Bayesian Quantile Regression ◽  
Prestressing Force ◽  
Quantile Regression Method

In the design of prestressing concrete structures, the friction characteristics between strands and channels have an important influence on the distribution of prestressing force, which can be considered comprehensively by curvature and swing friction coefficients. However, the proposed friction coefficient varies widely and may lead to an inaccurate prestress estimation. In this study, four full-scale field specimens were established to measure the friction loss of prestressing tendons with electromagnetic sensors and anchor cable dynamometers to evaluate the friction coefficient. The least square method and Bayesian quantile regression method were adopted to calculate the friction coefficient, and the results were compared with that in the specifications. Field test results showed that Bayesian quantile regression method was more effective and significant in the estimation of the friction coefficient.

Intercomparison of an Ensemble Kalman Filter with Three- and Four-Dimensional Variational Data Assimilation Methods in a Limited-Area Model over the Month of June 2003

2011 ◽  
Vol 139 (2) ◽  
pp. 566-572 ◽  
Author(s):  
Meng Zhang ◽  
Fuqing Zhang ◽  
Xiang-Yu Huang ◽  
Xin Zhang
Keyword(s):  
Kalman Filter ◽  
Data Assimilation ◽  
Ensemble Kalman Filter ◽  
Forecast Error ◽  
Wrf Model ◽  
Warm Season ◽  
Variational Data Assimilation ◽  
Lead Times ◽  
Limited Area ◽  
Forecast Errors

Abstract This study compares the performance of an ensemble Kalman filter (EnKF) with both the three-dimensional and four-dimensional variational data assimilation (3DVar and 4DVar) methods of the Weather Research and Forecasting (WRF) model over the contiguous United States in a warm-season month (June) of 2003. The data assimilated every 6 h include conventional sounding and surface observations as well as data from wind profilers, ships and aircraft, and the cloud-tracked winds from satellites. The performances of these methods are evaluated through verifying the 12- to 72-h forecasts initialized twice daily from the analysis of each method against the standard sounding observations. It is found that 4DVar has consistently smaller error than that of 3DVar for winds and temperature at all forecast lead times except at 60 and 72 h when their forecast errors become comparable in amplitude, while the two schemes have similar performance in moisture at all lead times. The forecast error of the EnKF is comparable to that of the 4DVar at 12–36-h lead times, both of which are substantially smaller than that of the 3DVar, despite the fact that 3DVar fits the sounding observations much more closely at the analysis time. The advantage of the EnKF becomes even more evident at 48–72-h lead times; the 72-h forecast error of the EnKF is comparable in magnitude to the 48-h error of 3DVar/4DVar.

Herding behavior in Islamic GCC stock market: a daily analysis

2018 ◽  
Vol 11 (2) ◽  
pp. 182-193 ◽  
Author(s):  
Mustapha Chaffai ◽  
Imed Medhioub
Keyword(s):  
Stock Market ◽  
Quantile Regression ◽  
Financial Markets ◽  
Stock Returns ◽  
Stock Markets ◽  
Content Type ◽  
Quantile Regression Analysis ◽  
Herd Behaviour ◽  
The Impact ◽  
Quantile Regression Method

Purpose This paper aims to examine the presence of herd behaviour in the Islamic Gulf Cooperation Council (GCC) stock markets following the methodology given by Chiang and Zheng (2010). Generalized auto regressive conditional heteroskedasticity (GARCH)-type models and quantile regression analysis are used and applied to daily data ranging from 3 January 2010 to 28 July 2016. Results show evidence of herd behaviour in the GCC stock markets. When the data are divided into down and up market periods, herd information is found to be statistically significant and negative during upward market periods only. These results are similar to those reported in some emerging markets such as China, Japan and Hong Kong, where stock returns perform more similarly during down market periods and differently during rising markets. Design/methodology/approach The authors present a brief literature on herd behaviour. Second, the authors provide some specificity of the GCC Islamic stock market, followed by the presentation of the methodology and the data, results and their interpretation. Findings The authors take into account the difference existing in market conditions and find evidence of herding behaviour during rising markets only for GCC markets. This result was confirmed after using the quantile regression method, as evidence of herding was observed only in highly extreme periods. Stock returns perform more similarly when market is down in Islamic GCC stock market. Research limitations/implications The research limitation consists in the fact that this work can be extended to compare the GCC stock markets with other markets in Asia such as Malaysia and Indonesia. Practical implications The principal implication consists in the fact that herding behaviour is limited in the GCC markets and Islamic finance can have an important contribution to moderate the behaviour in the financial markets. Social implications The work focusses on the role of ethics in the financial markets and their ability to reduce the impact of behavioural biases. Originality/value The paper studies the behaviour of investors in the Islamic financial markets and gives an idea about the importance of the behaviour in this particular market regarding its characteristics.

Sign in / Sign up

Export Citation Format

Share Document