Example for Practice
Q2. Multiple regressions Models are estimated and gives the following results:
Model I Model II
Dependent Variable: CPI Dependent Variable: CPI
Method: Least Squares Method: Least Squares
Date: 10/30/24 Time: 22:27 Date: 10/30/24 Time: 22:28
Sample (adjusted): 2001M07 2024M06 Sample (adjusted): 2001M08 2024M06
Included observations: 276 after adjustments Included observations: 275 after adjustments
Variable Coefficient Std. Errort-Statistic Prob. Variable Coefficient Std. Error t-Statistic Prob.
C -28.56 1.80 -15.87 0.0000 C -2.55 0.41 -6.27 0.0000
EXH 0.81 0.01 68.80 0.0000 EXH 0.07 0.01 8.63 0.0000
X 0.02 0.00 13.41 0.0000 X 0.00 0.00 4.00 0.0001
CPI(-1) 0.93 0.01 96.38 0.0000
R-squared 0.979 Mean dependent var92.96 R-squared 0.999 Mean dependent var 93.18
Adjusted R-squared 0.979 S.D. dependent var 55.74 Adjusted R-squared 0.999 S.D. dependent var 55.72
S.E. of regression 8.159 Akaike info criterion 7.05 S.E. of regression 1.376 Akaike info criterion 3.49
Sum squared resid 18175 Schwarz criterion 7.09 Sum squared resid 513 Schwarz criterion 3.54
Log likelihood -969.489 Hannan-Quinn criter.7.06 Log likelihood -475.868 Hannan-Quinn criter. 3.51
F-statistic 6280.181 Durbin-Watson stat 0.32 F-statistic 149767.800 Durbin-Watson stat 1.90
Prob(F-statistic) 0.0000 Prob(F-statistic) 0.0000
From the above output of both multiple regression equations, write the equations
in standard form and interpret the result about the significance for regression
equation as whole and the regression parameters independently. Compare
regression results of both outputs and find out which of the regression equation is
fit for forecasting. Forecast the M by using the following values:
Variables Dec-23 Jan-24 Feb-24 Mar-24 Apr-24 May-24 Jun-24
CPI 255.25
Exh 283.30 280.32 279.18 278.96 278.14 278.25 278.44
X 2822 2792 2583 2572 2351 2839 2560