Gas prices 2016. We have data on the weekly average retail price (cents per gallon) of regular gas nationwide.

We’ll extract the data from 2011 through June 2013.

Here’s a time series plot.

Here are a 4-point moving average and a 3-term autoregressive model fit to these data.

Dependent variable is: gas 130 total cases of which 3 are missing R squared = 95.5% R squared (adjusted) = 95.4%
s = 0.0440 with 127 - 4 = 123 degrees of freedom Variable Coefficient SE(Coeff) t-ratio P-value Intercept 0.258788 0.0703 3.68 0.0003 Lag1 1.55336 0.0901 17.2 60.0001 Lag2 -0.610098 0.1568 -3.89 0.0002 Lag3 -0.014045 0.0882 -0.159 0.8738 Which model is the better fit for the data?