Scribd
Upload
16 views11 pages

Regression Analysis of Sales and Income

The document presents regression analysis statistics, including multiple R, R square, and ANOVA results for sales prediction based on income and unemployment rates. It outlines steps for constructing various regression models, including residual analysis and Durbin-Watson tests for autocorrelation. The analysis covers sales forecasts for 2007 using different approaches and emphasizes the importance of comparing outcomes with lecture slides.

Uploaded by

DILAN GUNANA
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as XLSX, PDF, TXT or read online on Scribd
16 views11 pages

Regression Analysis of Sales and Income

The document presents regression analysis statistics, including multiple R, R square, and ANOVA results for sales prediction based on income and unemployment rates. It outlines steps for constructing various regression models, including residual analysis and Durbin-Watson tests for autocorrelation. The analysis covers sales forecasts for 2007 using different approaches and emphasizes the importance of comparing outcomes with lecture slides.

Uploaded by

DILAN GUNANA
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as XLSX, PDF, TXT or read online on Scribd

SUMMARY OUTPUT

Regression Statistics
Multiple R 0.99769311
R Square 0.99539155
Adjusted R S 0.99508432
Standard Erro 0.47666935
Observations 17

ANOVA
df SS MS F Significance F
Regression 1 736.147089 736.147089 3239.88904 6.08428E-19
Residual 15 3.40820509 0.22721367
Total 16 739.555294

CoefficientsStandard Error t Stat P-value Lower 95% Upper 95%


Intercept -1.5046209 0.32902638 -4.57294913 0.00036612 -2.20592403 -0.80331777
Income ($mill 0.02919162 0.00051285 56.9200232 6.08428E-19 0.0280985 0.03028474
Lower 95,0% Upper 95,0%
-2.20592403 -0.80331777
0.0280985 0.03028474
Year Sales ($millions) Income ($millions) Unemployment Rate Y lagged
1990 8 336.1 5.5
1991 8.2 349.4 5.5 8
1992 8.5 362.9 6.7 8.2
1993 9.2 383.9 5.5 8.5
1994 10.2 402.8 5.7 9.2
1995 11.4 437 5.2 10.2
1996 12.8 472.2 4.5 11.4
1997 13.6 510.4 3.8 12.8
1998 14.6 544.5 3.8 13.6
1999 16.4 588.1 3.6 14.6
2000 17.8 630.4 3.5 16.4
2001 18.6 685.9 4.9 17.8
2002 20 742.8 5.9 18.6
2003 21.9 801.3 5.6 20
2004 24.9 903.1 4.9 21.9
2005 27.3 983.6 5.6 24.9
2006 29.1 1076.7 8.5 27.3

By using the data sheet in "Sales in [Link]" file (Data), complete the following four points:

i. Construct a regression model with variables: Response: Sales, Predictor: Income (Slide-18).
Create a new sheet for your regression output. Copy the residuals from the regression output (select resid
Apply DW test and make interpretation using Sheet1.

ii. Construct a regression model with variables: Response: Sales, Predictors: Income, Unemployment Rate
Create a new sheet for your regression output. Copy the residuals from the regression output (select resid
Apply DW test and make interpretation using Sheet2.

iii. Construct a regression model with the sales-lag approach (Slide-20).


Find the point forecast for 2007 by using the regression's formula. Create a new sheet for your regression
Copy the residuals from the regression output (select residual output on Data analysis toolpak) paste them
You will be able to compute the residual autocorrelations. Compare them with the SE(r_k) and comment o

iv. Construct a regression model with the difference approach: forecast the sales difference by using the in
Apply DW test and make interpretation. Create a new sheet for your regression output.
Copy the residuals from the regression output (select residual output on Data analysis toolpak) paste them
Find the point forecast by using the regression's formula. Find the point forecast for 2007 by using the regr

Overall, please aim to observe the similar outcomes, which are shared in the lecture slides of the same da
n output (select residual output on Data analysis toolpak) paste them in the residuals column on Sheet1.

Unemployment Rate. (Slide-19)


n output (select residual output on Data analysis toolpak) paste them in the residuals column on Sheet2.

t for your regression output.


s toolpak) paste them in the residuals column on Sheet3.
(r_k) and comment on the possibility of autocorrelation on that lag.

rence by using the income difference (Slide-21).

s toolpak) paste them in the residuals column on Sheet4.


007 by using the regression's formula.

slides of the same data set. Forecast values are to be calculated using the regression formulas.
mn on Sheet1.

mn on Sheet2.
Residuals lag 1 (e_t-e_t-1)^2 e_t^2

DW

⍺ 0.05
# predictors 1
n 17
d_L 1.13
d_U 1.38
Residuals lag 1 (e_t-e_t-1)^2 e_t^2

DW

⍺ 0.05
# predictors 2
n 17
d_L 1.02
d_U 1.54
Residuals lag 1 lag 2 lag 3 lag 4 lag 5 lag 6

0.00
0.00 0.00
0.00 0.00 0.00
0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00
0.00 0.00 0.00 0.00 0.00 0.00

#DIV/0!
Denumerator lag 1 lag 2 lag 3 lag 4
#DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!
#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!

#DIV/0! #DIV/0! #DIV/0! #DIV/0! #DIV/0!

r_k #DIV/0! #DIV/0! #DIV/0! #DIV/0!

SE(r_k) 2/sqrt(16) 0.5


lag 5 lag 6

#DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!
#DIV/0! #DIV/0!

#DIV/0! #DIV/0!

#DIV/0! #DIV/0!
Residuals lag 1 (e_t-e_t-1)^2 e_t^2

DW

⍺ 0.05
# predictors 1
n 16
d_L 1.1
d_U 1.37

You might also like