Run Q on the regressors: P (price), I (income), other variables and lagged Q to capture habit forming. Skip the first row because of the empty cell in this row.
From the regression output, write down the estimated linear demand equation with t-statistics under the estimated coefficients. In addition, write down the R-square? Statistical significance of T-statistics is given by the P-values. There are three levels of significance: 1%, 5% and 10%. Ignore the P-values given in this output because the sample period is very small. Instead, use the following standard significance levels
If t-statistics < 1.63 (plus or minus) then there is no statistical significance at any level.
If 1.63 < t-statistics < 1.96, there is statistical significance at the 10% level.
If 1.96 < t-statistics < 2.54, there is statistical significance at the 5% level
If t-statistics > 2.54, there is statistical significance at the 1% level.
Calculate the short run and long run price and income elasticities of demand from the estimated coefficients in the regression equation, using the averages for the quantity, price and income (skip the first row when you calculate the averages)
Short Run P-elasticity for a linear Eq. = slope of price*(average price/average quantity)
Long Run P -elasticity for a linear Eq. = [slope of price / (1- slope of the lagged variable)]*(average Price/average quantity).
Short Run I- elasticity for a linear Eq. = slope of income*(average income/average quantity)
Long Run P- elasticity for a linear Eq. = [slope of income / (1- slope of the lagged variable)]*(average income/average quantity).
Average = sum/n (skip first row).
The short-run and long run income elasticities are calculated the same way. Here the slope is for income.
Can you think of another independent variable that you may add to the above equation? What will the sign of this variable be? Specify the name...