In: Statistics and Probability
USING MINITAB
13.2 - Multiple Linear Regression Exercise – Stock Price
Data File: as above
The stock broker now wants to include additional predictor variables to determine the driving factors for the stock price increase of Company A. Perform a multiple linear regression analysis between Company A and the 10 Yr. T, GDP and Unemployment (columns C1, C3, C4, and C5). Use the Minitab data file Regression.MTW.
Company A Company B 10-Yr T
GDP ($millions) Unemployment
36.25 30 2.33
7308755 0.049999
37.25 31.13 2.35
7664060 0.0489
37.75 29.63 2.59
8100201 0.046998
38.25 29.75 2.35
8608515 0.0456518012316533
39.88 34.25 2.33
9089168 0.0455796
40.88 32.13 2.39
9660624 0.0440165865291262
39.13 30.88 2.35
10284779 0.0434307310031873
40 39.13 2.26
10621824 0.0430990467039838
41.5 42.38 2.61
10977514 0.0430125479866333
38.63 35.88 2.34
11510670 0.0424427282488884
40.13 32 2.37
12274928 0.0418140882794917
41.88 46.13 2.37
13093726 0.0417299158834746
40.5 42.88 2.46
13855888 0.0412573398952287
42.75 47.5 2.78
14477635 0.041
42.88 49.25 2.81
14718582 0.040777693159957
42.5 46.5 2.73
14418739 0.0407039599845414
41.13 45.25 2.97
14964372 0.0406274797887733
43.5 54.88 2.89
15517926 0.0402249821009884
42.88 48.88 2.87
16155255 0.039987
43.75 56.25 3
16691517 0.0398462357373634
44 60.13 2.9
17427609 0.0396872926778427
44.5 56.88 3.09
18120714 0.0390638072400817
43.88 59.75 3.14
18624475 0.03758
45.5 60.25 3.17
19390604 0.03665
Solution:
Here, we have to use regression model for the prediction of the dependent variable Company A based on the independent variables such as 10 Yr. T, GDP and Unemployment.
A regression model by using Minitab is given as below:
Welcome to Minitab, press F1 for help.
Regression Analysis: Company A versus 10-Yr. T, GDP ($millions), ...
The regression equation is
Company A = 50.3 + 1.70 10-Yr. T +0.000000 GDP ($millions) - 378 Unemployment
Predictor Coef SE Coef T P
Constant 50.28 10.11 4.97 0.000
10-Yr. T 1.696 1.482 1.14 0.266
GDP ($mi 0.00000019 0.00000025 0.74 0.471
Unemploy -378.0 207.2 -1.82 0.083
S = 0.8913 R-Sq = 88.9% R-Sq(adj) = 87.2%
Analysis of Variance
Source DF SS MS F P
Regression 3 127.109 42.370 53.33 0.000
Residual Error 20 15.890 0.794
Total 23 142.999
Source DF Seq SS
10-Yr. T 1 99.236
GDP ($mi 1 25.230
Unemploy 1 2.644
Unusual Observations
Obs 10-Yr. T Company Fit SE Fit Residual St Resid
10 2.34 38.630 40.344 0.331 -1.714 -2.07R
R denotes an observation with a large standardized residual
The P-value for this regression model is given as 0.00 which indicate that the given regression model is statistically significant and we can use this regression model for the prediction of the dependent variable.
The regression equation is given as below:
Company A = 50.3 + 1.70 10-Yr. T +0.000000 GDP ($millions) - 378 Unemployment
The coefficient of determination or the value of R square is given as 0.889 which means about 88.9% of the variation in the dependent variable is explained by the independent variable.