Liquefied petroleum gas (LPG) is rapidly becoming a key part of Cameroon's energy mix, with enormous future potential. However, there are still many uncertainties about the extent of its potential market, which has so far often led to supply shortages. These shortages therefore constitute a major obstacle to the objective of promoting LPG as the main fuel in Cameroonian households. Accordingly, the short and long-run elasticities of LPG consumption in Cameroon are investigated in this work. This work uses annual time series data from 1994 to 2017. A basic model and four alternative specifications are used. Mid-run price and income elasticities of LPG consumption are found to be between −0.330 and −0.401, and, 0.159 and 0.569, respectively. Of all the five models, the error correction model is the most robust and the elasticities estimates reveal that price, income and urbanization are important determinants of LPG consumption in Cameroon. These results are consistent with those given by the other models, and in line with previous research on developing countries whose economic and demographic situation is similar to that of Cameroon. These results have serious implications on demand side management and calls for policy makers to promote widespread use of LPG especially in the savannah zone in order to reduce deforestation and overdependence on biomass.
1 January 2024 in Computational and Mathematical Methods
Grey systems theory can be used to predict the evolution of a system with insufficient information. Unfortunately, the most used version of the grey model (GM), namely, GM(1,1), works best when the system series have an increasing exponential rate. In any other case, the GM(1,1) produces inaccurate predictions. In this paper, we examine the mathematical formulation of the conventional GM(1,1) in order to propose a new GM that addresses its shortcomings through a new time response function. Examples are presented to demonstrate the flexibility and accuracy of the new model when implemented with series of various natures. Comparisons with other intelligent GM(1,1) show that the proposed model performs better than the reference models.