Regional Workshop on Energy Statistics and Modeling for the SDG7 and the COP21 INDC Energy Targets 1418 March 2016 Nukualofa Kingdom of Tonga Introduction to EconomicSocioeconomic Data and their Relation to Energy Consumption ID: 624941
Download Presentation The PPT/PDF document " Joint SPC-APEC" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Joint SPC-APEC
Regional Workshop on Energy Statistics and Modeling for the SDG7 and the COP21 INDC Energy Targets
14-18 March 2016Nuku’alofa, Kingdom of TongaIntroduction to Economic/Socio-economic Data and their Relation to Energy ConsumptionEdito BarcelonaEnergy Statistics and Training OfficeAsia Pacific Energy Research Centre
Session 3-CSlide2
The Reference Energy SystemSlide3
Need of forecasting Energy Demand
Energy is
a driver of economic activities
Thus energy should be used wiselyFor this, countries need to have plans for their future energy use and supplyModels have been used to forecast energy demand and to estimate supply to meet these demandThe most common approach is econometric modeling which links energy demand with socio-economic activitiesSlide4
Energy and Economy
Energy consumption and economic activity are known to be correlated although the relationship is not necessarily absolute.
Energy is a required input for economic activity
Relationship between energy and the economy can be expressed in a mathematical equationSlide5
Final Demand
Industry / Residential & Commercial / Transport
Conversion SectorElectricity / Oil Refineries/Gas PlantsPrimary Energy DemandMacro-Economic ModelGDP components/ energy price/industrial activitiesModel StructureSlide6
Econometric Demand Function
Top down approach
Linking macro-economic model with energy model
Demand functions such as:E = f(Y, Pe/CPI) or E = f(Y, Pe/CPI, E-1)whereE: Energy DemandY: IncomePe: Energy PriceCPI: Consumer Price IndexPe/CPI: Relative priceE-1: Energy Demand at previous periodSlide7
Energy Demand Modeling
Formulation of theoretical demand model
e.g.: Y = f(X
1, X2, X3)Estimation: to measure quantitative relation among key variablesY = α + β1 X1 + β2 X2 + β3X3 + u => Given historical Xi and Y
estimate
α
^
and
β
i
^
Projection:
Given
α
^
,
β
i
^
and future
values
of
X
i
,
get future value of Y
*
Example: Y is energy demand, X
1
is GDP, X
2
is Price,
X
3
is Lag variableSlide8
Regression Analysis
Issue
: how to estimate the parameters α and βMethod of OLS (Ordinary Least Squares)
Minimize the sum of squared residuals: minui^2= (yi- α^- β^xi) ^2Key Assumptions for OLS to be ValidZero conditional mean: E(u/x) = 0Homoskedasticity: Var(u/x) = constant, no heteroskedasticity and serial correlation (autocorrelation) of error termsSlide9
Forms of Regression Functions
Level-Level Form
- Y = α + β X + U => Interpret: ΔY = β Δ X - Y = α + β1 X + β2 X2 + U => Interpret: ΔY = (β1 + 2 β2 X)Δ XLog-Log Form: elasticity of Y
w.r.t
. X
- log Y = α + β
log X + U
=> Interpret: %ΔY = β %Δ
X
Log-Level Form: semi-elasticity of Y
w.r.t
. X
- log Y = α + β
X + U
=> Interpret: %ΔY = (100*β) Δ
X
Level-Log Form: not frequently used
- Y = α + β
log X + U
=> Interpret: ΔY = (β/100)% Δ
XSlide10
Procedure in Estimation & Forecast
1. Start with
established facts or economic theories
2. Analyze historical data3. Identify explanatory variables4. Specify the model and test it 5. Check the fitted values.6. If not “good-fit”. Re-
test
with other
variable
s
7. Select the “good-fit” and use for forecastingSlide11
Economic Activity
Indicators
Industry sector: Index of Industrial Production (IIP) by sub-sectors, amounts of production by
sub-sectors likes tons of steel, cement, pulp, paper, etcTransport sector: Number of vehicles, transport demand such passenger-kms or ton-kms of freight, etcResidential sector: Number of households, per capita income, number of appliances, etcCommercial sector: Area of office building, private consumption, GDP of services, etcSlide12
Prices
Primary
energyCrude Oil Coal price
Gas priceSecondary energyPetroleum productsElectricitySlide13
Estimation of Final Energy Demand
Industry Sector:
Coal: Coking coal, Steam coal, Sub-bituminous coal and LigniteOil: LPG, Naphtha, Kerosene, Diesel and Fuel oilGas: Natural Gas, Coal gas and petroleum gasElectricity
New and renewable energySlide14
Estimation of Final Energy Demand
Transport Sector
:Road: LPG, Gasoline, Diesel, Natural gas and Electricity
Rail: Coal, Diesel and ElectricityAir: Aviation gasoline and Jet keroseneInland waterways: Gasoline, Diesel and Fuel oilSlide15
Estimation of Final Energy Demand
Other Sector: Residential: LPG, Kerosene, Natural Gas and Electricity
Commercial: LPG, Kerosene,
Diesel, Fuel Oil, Natural Gas and Electricity Slide16
www.ieej.or.jp/egeda/
16
Thank you for your attention