Inflationary effects of oil prices and domestic gasoline prices:Markov-switching-VAR analysis

The purpose of this study is to contribute to the literature by studying the effects of sudden changes both on crude oil import price and domestic gasoline price on inflation for Turkey, an emerging country. Since an inflation targeting regime is being carried out by the Central Bank of Turkey, determination of such effects is becoming more important. Therefore empirical evidence in this paper will serve as guidance for those countries, which have an in- flation targeting regime. Analyses have been done in the period of October 2005-December 2012 by Markovswitching vector autoregressive （MS-VAR） models which are successful in capturing the nonlinear properties of variables. Using MS-VAR analysis, it is found that there are 2 regimes in the analysis period. Furthermore, regime changes can be dated and the turning points of economic cycles can be determined. In addition, it is found that the effect of the changes in crude oil and domestic gasoline prices on consumer prices and core inflation is not the same under different regimes. Moreover, the sudden increase in gasoline price is more important for consumer price infla- tion than crude oil price shocks. Another finding is the presence of a pass-through effect from oil price and ga- soline price to core inflation.

A Novel Hybrid Model for Gasoline Prices Forecasting Based on Lasso and CNN

Gasoline is the lifeblood of the national economy.The forecasting of gasoline prices is difficult because of frequent price fluctuations,its complex nature,diverse influencing factors,and low accuracy of prediction results.Previous studies mainly focus on forecasting gasoline prices in a single region by single time series analysis which ignores the daily price co-movement of different series from multiple regions.Because price co-movement may contain useful information for price forecasting,this paper proposes the LassoCNN ensemble model that combines statistical models and deep neural networks to forecast gasoline prices.In this model,the Least Absolute Shrinkage and Selection Operator(Lasso)screens and chooses the correlated time series to enhance the performance of forecasting and avoid overfitting,while Convolutional Neural Network(CNN)takes the selected multiple series as its input and then forecasts the gasoline prices in a certain region.Forecasting results of gasoline prices at the national level and regional levels by using the new method demonstrate that the new approach provides more accurate results for the predictions of gasoline prices than those results generated by alternative methods.Thus,the relevant series can enhance the performance of forecasting and help to gain better results.