Question

In an attempt to "time the market," a financial analyst studies the quarterly returns of a stock. He uses the model y = Bo + $1d1 + B2d2 + B3d3 + E where y is the quarterly return of a stock, dy is a dummy variable that equals 1 if quarter 1 and 0 otherwise, da is a dummy variable that equals 1 if quarter 2 and 0 otherwise, and dz is a dummy variable that equals 1 if quarter 3 and O otherwise. The following table shows a portion of the regression results. 10 points Coefficients Intercept 12.56 5.23 -1.20 -8.79 Standard Errort 7.82 2.52 .52 2.60 Stat 1.61 -2.08 -2.31 -3.38 p-value 0.12 0.04 0.03 0.00 eBook Files a-1. Given that there are four quarters in a year, why doesn't the analyst include a fourth dummy variable in his model? Print O Inclusion of de would cause perfect multicollinearity. O Inclusion of de would cause changing variance. Inclusion of de would cause correlated residuals. O Inclusion of de would cause dy to be significant References a-2. What is the reference category? Quarter 1 Quarter 2 Quarter 3 Quarter 4

Answer 1

a-1)
option A)
we need only n-1 dummy variable for n levels
d1+d2+d3+d4 = 1

a-2)
since d4 is not there , quarter 4 is reference category

option D)

b-1)

option A)

if p-value < alpha, we reject the null hypothesis

b-2

Yes