In a 1997 paper, Borenstein, Cameron, and Gilbert (BCG) claim that gasoline prices rise quickly following an increase in the price of crude oil, but fall slowly following a decrease. This note estimates an error-correction model with daily spot gasoline and crude-oil price data over the period 1985–1998 and finds no evidence of asymmetry in wholesale gasoline prices. The sources of the difference in results are twofold. First, we use the standard Engle-Granger two-step estimation procedure, whereas BCG used a nonstandard estimation methodology. Second, even using BCG's nonstandard specification, the use of daily rather than weekly data yields little evidence of price asymmetry.

This paper reexamines the benefits of pooling and, in addition, contrasts the performance of newly proposed heterogeneous estimators. The analysis utilizes a panel data set from 46 American states over the period 1963 to 1992 and a dynamic demand specification for cigarettes. Also, the forecast performance of the various estimators is compared.