scholarly journals Automatic time series modeling and forecasting: A replication case study of forecasting real GDP, the unemployment rate and the impact of leading economic indicators

2020 ◽  
Vol 8 (1) ◽  
pp. 1759483
Author(s):  
John Guerard ◽  
Dimitrios Thomakos ◽  
Foteini Kyriazi ◽  
Xibin Zhang
Keyword(s):  
Time Series ◽  
Unemployment Rate ◽  
Economic Indicators ◽  
Time Series Modeling ◽  
Real Gdp ◽  
Modeling And Forecasting ◽  
Leading Economic Indicators ◽  
The Impact

scholarly journals Time Series Modeling of Air Pollution and Its Association with Season and Climate Variables in Istanbul, Turkey

2020 ◽  
Author(s):  
hazem al-najjar ◽  
Nadia Al-Rousan ◽  
Ismail A. Elhaty
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Feature Selection ◽  
Wind Speed ◽  
Air Pollutants ◽  
Time Series Modeling ◽  
Climate Variables ◽  
Different Seasons ◽  
The Impact

Abstract Air pollution depends on seasons, wind speed, temperature, wind direction and air pressure. The effect of different seasons on air pollution is not fully addressed in the reported works. The current study investigated the impact of season on air pollutants including SO2, PM10, NO, NOX, and O3 using NARX method. In the applied methodology, a feature selection was used with each pollutant to find the most important season(s). Afterward, six models are designed based on the feature selection to show the impact of seasons in finding the concentration of pollutants. A case study is conducted on Esenyurt which is one of the most populated and industrialized places in Istanbul to validate the proposed framework. The performance of using all of the designed models with different pollutants showed that using season effect led to improving the performance of predictor and generating high R2 and low error functions.

scholarly journals Time series modeling of air pollution and its association with season and climate variables in istanbul, turkey

2020 ◽  
Author(s):  
hazem al-najjar ◽  
Nadia Al-Rousan ◽  
Ismail A. Elhaty
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Feature Selection ◽  
Air Pollutants ◽  
Time Series Modeling ◽  
Climate Variables ◽  
Different Seasons ◽  
The Impact ◽  
Nonlinear Autoregressive

Abstract Air pollution depends on seasons, wind speed, temperature, wind direction and air pressure. The effect of different seasons on air pollution is not fully addressed in the reported works. The current study investigated the impact of season on air pollutants including SO2, PM10, NO, NOX, and O3 using Nonlinear AutoregRessive network with eXogenous inputs (NARX) method. In the applied methodology, a feature selection was used with each pollutant to find the most important season(s). Afterward, six models are designed based on the feature selection to show the impact of seasons in finding the concentration of pollutants. A case study is conducted on Esenyurt which is one of the most populated and industrialized places in Istanbul to validate the proposed framework. The performance of using all of the designed models with different pollutants showed that using season effect led to improving the performance of predictor and generating high R2 and low error functions.

scholarly journals Time series modeling of air pollution and its association with season and climate variables in istanbul, turkey

2020 ◽  
Author(s):  
hazem al-najjar ◽  
Nadia Al-Rousan ◽  
Ismail A. Elhaty
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Feature Selection ◽  
Air Pollutants ◽  
Time Series Modeling ◽  
Climate Variables ◽  
Different Seasons ◽  
The Impact ◽  
Nonlinear Autoregressive

Abstract Air pollution depends on seasons, wind speed, temperature, wind direction and air pressure. The effect of different seasons on air pollution is not fully addressed in the reported works. The current study investigated the impact of season on air pollutants including SO2, PM10, NO, NOX, and O3 using Nonlinear AutoregRessive network with eXogenous inputs (NARX) method. In the applied methodology, a feature selection was used with each pollutant to find the most important season(s). Afterward, six models are designed based on the feature selection to show the impact of seasons in finding the concentration of pollutants. A case study is conducted on Esenyurt which is one of the most populated and industrialized places in Istanbul to validate the proposed framework. The performance of using all of the designed models with different pollutants showed that using season effect led to improving the performance of predictor and generating high R2 and low error functions.

scholarly journals Time series modeling of air pollution and its association with season and climate variables in istanbul, turkey

2020 ◽  
Author(s):  
hazem al-najjar ◽  
Nadia Al-Rousan ◽  
Ismail A. Elhaty
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Feature Selection ◽  
Air Pollutants ◽  
Time Series Modeling ◽  
Climate Variables ◽  
Different Seasons ◽  
The Impact ◽  
Nonlinear Autoregressive

Abstract Air pollution depends on seasons, wind speed, temperature, wind direction and air pressure. The effect of different seasons on air pollution is not fully addressed in the reported works. The current study investigated the impact of season on air pollutants including SO2, PM10, NO, NOX, and O3 using Nonlinear AutoregRessive network with eXogenous inputs (NARX) method. In the applied methodology, a feature selection was used with each pollutant to find the most important season(s). Afterward, six models are designed based on the feature selection to show the impact of seasons in finding the concentration of pollutants. A case study is conducted on Esenyurt which is one of the most populated and industrialized places in Istanbul to validate the proposed framework. The performance of using all of the designed models with different pollutants showed that using season effect led to improving the performance of predictor and generating high R2 and low error functions.

Market overreaction, firm-specific information and macroeconomic variables in US and Chinese markets during COVID-19

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ooi Kok Loang ◽  
Zamri Ahmad
Keyword(s):  
Unemployment Rate ◽  
Stock Return ◽  
Design Methodology ◽  
Specific Information ◽  
Content Type ◽  
Macroeconomic Variables ◽  
Real Gdp ◽  
Chinese Markets ◽  
The Impact ◽  
Loser Portfolio

PurposeThis study examines the impact of firm-specific information and macroeconomic variables on market overreaction of US and Chinese winner and loser portfolio before and during COVID-19.Design/methodology/approachThe firm-specific information includes firm size, volume, volatility, return of asset (ROA), return of equity (ROE), earning per share (EPS) and quick ratio while the macroeconomic variables are export rate, import rate, real GDP, nominal GDP, FDI, IPI and unemployment rate. Besides, one-third of the top performance stocks are categorized as winner portfolio while one-third of lowest performance stocks are categorized as loser portfolio. This study uses AECR to indicate stock return and measure market overreaction. GAECR is used to determine contrarian profit. The data range of pre-COVID-19 is from 1-Jan-2015 to 31-Dec-2019 while the period of COVID-19 is from 1-Jan-2020 to 31-Dec-2020.FindingsIn pre-COVID-19, firm-specific information (volatility, ROA, ROE and EPS) and macroeconomic variables are found to be correlated to stock return in US and Chinese portfolios except Chinese winner portfolio. Nonetheless, the impact of firm-specific information has vanished and macroeconomic variables are significant to stock return in COVID-19. It shows that investors rely on the economic indicators to trade in turbulent period due to emergence of COVID-19 as a disruption in market. Furthermore, US and Chinese portfolios are overreacted during COVID-19. Chinese loser portfolio has higher tendency of overreaction than US loser portfolio while US winner portfolio has higher tendency of overreaction than Chinese winner portfolio.Originality/valueThe results of this study assists academician, practitioners and investors on understanding and create awareness to the existence of market overreaction and the determinants that can cause the phenomenon.

Sign in / Sign up

Export Citation Format

Share Document