Question See attachment for questions:

03 Jun Question See attachment for questions:

Question
See attachment for questions:

Suppose we want to investigate the money spending behavior in the US, by using the following model

M2t = fio + PiGDPt + fcFFRt + fijnflationt + st

C P l t — C P l t— 4 where ?2: money supply, GDP: Gross Domestic Product, FFR: interest rate, lnflation= — — * 100

and CPI: Consumer Price Index.

We expect thatf)i >0,<0, /?? > 0

We want to test the seasonality effect to see if the US money supply is larger during the Thanksgiving and Christmas

holidays (last quarter of the year).

The quarterly dummy variables are defined as

51 = 1 for Quarter 1, = 0 otherwise S3 =1 for Quarter 3, = 0 otherwise

52 = 1 for Quarter 2, = 0 otherwise S4 =1 for Quarter 4, = 0 otherwise

After regressing without the dummy variables we get the following results:

Dependent Variable: ?2

Method: Least Squares

Date: 09/05/14 Time: 14:06

Sample (adjusted): 1991Q1 2008Q4

Included observations: 72 after adjustments

Question 1 (25%)

Variable Coefficient Std. Error t-Statistic Prob.

? 17.35961 104.2171 0.166572 0.8682

GDP 0.533719 0.007350 72.61667 0.0000

FFR -106.6752 11.36128 -9.389367 0.0000

INFLATION 92.00183 20.81161 4.420698 0.0000

R-squared 0.990164 Mean dependent var 5015.053

Adjusted R-squared 0.989730 S.D. dependent var 1455.821

S.E. of regression 147.5375 Akaike info criterion 12.87999

Sum squared resid 1480178. Schwarz criterion 13.00648

Log likelihood -459.6798 Hannan-Quinn criter. 12.93035

F-statistic 2281.682 Durbin-Watson stat 0.525617

Prob(F-statistic) 0.000000

A. Analyze the sign of the coefficients. Are they consistent with what we expect? Analyze the effect of

each coefficient to the dependent variable.

We now apply the seasonal effects (by adding dummy variables) to our model and we get the following outputs in

each case

Dependent Variable: M2

Method: Least Squares

Date: 09/05/14 Time: 14:07

Sample (adjusted): 1991Q1 2008Q4

Included observations: 72 after adjustments

Variable Coe fficient Std. Error t-Statistic Prob.

C 45.63989 107.8607 0.423137 0 .6736

GDP 0.533536 0.007399 72.10652 0.0000

FFR -106.5331 11.42487 -9.324662 0.0000

INFLATION 95.61539 21.09593 4.532409 0.0000

S1 -24.45142 49.73021 -0.491681 0.6246

S2 -63.74150 49.83238 -1.279118 0.2054

S3 -60.87846 49.74099 -1.223909 0.2254

R-squared 0.9 90495 Mean dependent var 501 5.053

Adjusted R-squared 0.989618 S.D. dependent var 1455.821

S.E. of regression 148.3399 Akaike info criterion 12.92905

Sum squared resid 1430307. Schwarz criterion 13.15040

Log likelihood -458.4460 Hannan-Quinn criter. 13.01717

F-statistic 1128.911 Durbin-Watson stat 0.492410

Prob(F-statistic) 0.000000

Dependent Variable: M2