What are the determinants of renewable energy consumption? An application for variable selection

被引:3
作者
Esenyel, Nimet Melis [1 ]
机构
[1] Istanbul Univ, Fac Econ, Dept Econometr, Istanbul, Turkiye
关键词
Renewable energy; Energy consumption; Variable/feature selection; Random forest; Bayesian model averaging; BAYESIAN MODEL SELECTION; RANDOM FOREST; LINEAR-REGRESSION; CO2; EMISSIONS; OIL PRICES; PREDICTION; GROWTH; CLASSIFICATION; UNCERTAINTY; CRITERION;
D O I
10.1016/j.renene.2024.122029
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This study aims to determine the factors influencing renewable energy in Turkiye. Three different variables are considered as indicators of renewable energy: renewable energy consumption, renewable energy production, and the share of renewable energy consumption in total energy consumption. A set of macroeconomic, socioeconomic, and energy-based variables considered as potential influencing factors for these indicators are treated as candidate independent variables. Three different models created with these candidate variables are estimated using Bayesian Model Averaging (BMA) and Random Forest (RF) methods. Additionally, the study investigates which variables are the most significant determinants of the considered indicators. The results indicate that social development and education play a critical role in driving renewable energy consumption. For renewable energy production, labor force and oil consumption are also found to be important, suggesting that energy transition requires not only technological investments but also policies targeting human resources and fossil fuel management. Finally, the findings show that greenhouse gas emissions are a key factor in increasing the share of renewables in total energy consumption, highlighting the importance of emission reduction policies in Turkiye's energy transition.
引用
收藏
页数:12
相关论文
共 84 条
[1]   Determinants of renewable energy growth: A global sample analysis [J].
Aguirre, Mariana ;
Ibikunle, Gbenga .
ENERGY POLICY, 2014, 69 :374-384
[2]  
AKAIKE H, 1973, BIOMETRIKA, V60, P255, DOI 10.2307/2334537
[3]   Modeling the determinants of renewable energy consumption: Evidence from the five most populous nations in Africa [J].
Akintande, Olalekan J. ;
Olubusoye, Olusanya E. ;
Adenikinju, Adeola F. ;
Olanrewaju, Busayo T. .
ENERGY, 2020, 206
[4]   MEAN SQUARE ERROR OF PREDICTION AS A CRITERION FOR SELECTING VARIABLES [J].
ALLEN, DM .
TECHNOMETRICS, 1971, 13 (03) :469-&
[5]  
[Anonymous], 2021, BP statistical review of world energy
[6]  
[Anonymous], 1999, Denge Tablolari (Energy Balance Tables)
[7]  
[Anonymous], Idaho Office of Drug Policy. (2020). 2020 update. Retrieved from https://odp.idaho.gov/wp-content/uploads/sites/114/2020/11/2017-2022-Idaho-OpioidMisuse-and-Overdose-Strategic-Plan-2020-Update-5.pdf
[8]   The causal dynamics between renewable energy, real GDP, emissions and oil prices: evidence from OECD countries [J].
Apergis, Nicholas ;
Payne, James E. .
APPLIED ECONOMICS, 2014, 46 (36) :4519-4525
[9]  
Apergis Nicholas., 2019, Anadolu Universitesi Sosyal Bilimler Dergisi, V19, P1, DOI [DOI 10.18037/AUSBD.566663, 10.18037/ausbd.566663]
[10]   Renewable energy policy effectiveness: A panel data analysis across Europe and Latin America [J].
Bersalli, German ;
Menanteau, Philippe ;
El-Methni, Jonathan .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2020, 133