Gasoline Price Forecasting
1 A Case Study on the Price of Gasoline
- Unleaded Regular Gasoline, U.S. City Average Retail Price, Monthly
- U.S. Crude Oil First Purchase Price, Monthly
- Civilian Unemployment Rate
- Housing Starts: Total: New Privately Owned Housing Units Started
- Real personal income excluding current transfer receipts
- Consumer Price Index for All Urban Consumers: All Items
1.1 Do you believe the ARIMA model can do the magic?
1.1.1 YES!
Give me your reasons.
1.1.2 NO!
Why?
1.2 Import the data
Gas_prices <- readxl::read_xlsx(path = "data/Gas_prices_1.xlsx")
colnames(Gas_prices)[1] “Date” “Year” “Month” “Unleaded”
[5] “Crude_price” “SP500” “PDI” “CPI”
[9] “RR_sales” “Unemp” “Housing” “Demand”
[13] “Production” “Imports” “Stocks” “Time”
[17] “L1_Unleaded” “L1_Crude_price” “L1_SP500” “L1_PDI”
[21] “L1_CPI” “L1_RR_sales” “L1_Unemp” “L1_Housing”
[25] “L1_Demand” “L1_Production” “L1_Imports” “L1_Stocks”
[29] “Recession”
if (!require("forecast")){install.packages("forecast")}1.3 Scatter plot between Unleaded and predictors
library("PerformanceAnalytics")
my_data1 <- Gas_prices[,-c(1:3,10:29)]
chart.Correlation(R = my_data1, histogram=TRUE, pch=19)
my_data2 <- Gas_prices[,-c(1:3,5:9, 16:29)]
chart.Correlation(R = my_data2, histogram=TRUE, pch=19)
my_data3 <- Gas_prices[,-c(1:3,5:16,23:29)]
chart.Correlation(R = my_data3, histogram=TRUE, pch=19)