A data set on gasoline demand in the OECD countries from 1960 to 1978
Format
A data frame with 342 observations on the following 6 variables.
countrya character vector for an English country name
yeara numeric vector for the year of observation
gasgasoline consumption per car, log-transformed
incomereal per capita income, log-transformed
pricereal gasoline price, log-transformed
carsthe stock of cars per capita (log-transformed)
Details
The data are a simple port from the AER package. Users should read Baltagi and Griffin (1983) for more information. The data are purely for illustration about panel models.
Generally, per capita income should not be negative when log-transformed, especially for this set of countries. While it is clear that such negative values arise from the logarithmic transformation of values less than 1, but more than 0, it is not clear why per capita income would be on that particular scale.