skip to main content

METODE REGRESI DATA PANEL UNTUK PERAMALAN KONSUMSI ENERGI DI INDONESIA


Citation Format:
Abstract

Panel data regression is a method that aims to model the effect of one or more predictor variables on the response variable, observed in some sectors of an object of research for a specific time period. To estimate the panel data regression model, there are three approaches, namely Common Effect Model (CEM), Fixed Effects Model (FEM) and Random Effects Model (REM). In estimating the parameters for each model, there are several methods that can be used based on the assumption of the structure residual variance-covariance matrix, that is Ordinary Least Square/Least Square Dummy Variable (OLS/LSDV), Weighted Least Square (WLS) dan Seemingly Unrelated Regression (SUR). This research aims to implement the panel data regression to analyze the effect of GDP on energy consumption in Indonesia for each sector. Panel data regression model that has been obtained then is used to predict the amount of energy consumption in Indonesia for each sector in 2015 and 2016 using trend analysis. The analysis showed that the panel data regression model corresponding to the data of energy consumption in Indonesia in 1990-2014 is Fixed Effect Model (FEM) with Cross-section SUR, with R2 value is 0.975943. Forecasting results show energy consumption in Indonesia in 2015 and 2016 will increase to the household sector and transport. Whereas for industrial, commercial and others sectors will decline in 2015 and then increase in 2016.

 

Keywords : Panel Data, Fixed Effect Model, SUR, Trend Analysis, Energy Consumption

Fulltext View|Download
Keywords: Panel Data, Fixed Effect Model, SUR, Trend Analysis, Energy Consumption

Article Metrics:

Last update:

No citation recorded.

Last update:

No citation recorded.