Você está na página 1de 25

Ross, Westerfield, and Jaffe's Spreadsheet Master

Corporate Finance, 9th edition


by Brad Jordan and Joe Smolira
Version 9.0

Chapter 12

In these spreadsheets, you will learn how to use the following Excel f
Multifactor Regression Estimates
The following conventions are used in these spreadsheets:
1) Given data in blue
2) Calculations in red
NOTE: Some functions used in these spreadsheets may require that
the "Analysis ToolPak" or "Solver Add-In" be installed in Excel.
To install these, click on the Office button
then "Excel Options," "Add-Ins" and select
"Go." Check "Analysis ToolPak" and
"Solver Add-In," then click "OK."

the following Excel functions:

adsheets:

Chapter 12 - Section 6
Empirical Approaches to Asset Pricing

The In Their Own Words box by Kenneth French at the end of the chapter details the three-factor APT model that i
returns. Estimating the three-factor model can be accomplished with a multi-factor regression in Excel. We went to
factor model, which you will find on the Return Data worksheet, along with the returns for Amazon.com. On the AM
three-factor APT regression estimate for Amazon.com stock.

We should note that the three factor data on the website may be a different scale than your return calculations. In
decimal while the excess return of the market in the data set may be 1.53 instead of .0153. What effect would it ha
independent variables?

RWJ Excel Tip


To estimate a multi-factor linear regression, go to the Data tab, Data Analysis, and select Regression, then OK the s

The input box for our linear regression looks like this:

The Y input range is the dependent variable, in this case the stock returns, and the X input range are the independe
data and selected the Labels box, which will put a label on the output for the variables. Finally, we selected the Con
interval. Because Excel will allow you to enter the X variables as an array, it is easier to make sure that the X variab

the three-factor APT model that is frequently used to explain the cross-section of average stock
or regression in Excel. We went to Ken French's website and gathered the data for the threeturns for Amazon.com. On the AMZN regression worksheet, you will find the results for the

than your return calculations. In other words, the return calculation for the stock in Excel is a
of .0153. What effect would it have on the regression if we did not change the scale of the

select Regression, then OK the same way we did for a single factor regression.

e X input range are the independent variables, or three-factors. We included the row above the
ables. Finally, we selected the Confidence Interval box and asked for a 95 percent confidence
er to make sure that the X variables are in adjacent columns in the data table.

SUMMARY OUTPUT
Regression Statistics
Multiple R
0.6305621
R Square
0.397608562
Adjusted R Square
0.364750847
Standard Error
0.118384814
Observations
59
ANOVA
df
Regression
Residual
Total

Intercept
Mkt - Rf
SMB
HML

3
55
58

SS
0.508781864
0.770823037
1.2796049

MS
F
Significance F
0.169593955 12.10091949
3.43155E-06
0.014014964

Coefficients
Standard Error
t Stat
P-value
0.027241749
0.015584172 1.748039572 0.086037618
1.705108114
0.388883473 4.384624783 5.28866E-05
1.037327198
0.777134503 1.334810376 0.187437779
-2.431024299
0.633287726 -3.838735856 0.000321599

Lower 95%
-0.003989629
0.925768224
-0.520085138
-3.700161253

Upper 95%
0.058473126
2.484448004
2.594739534
-1.161887345

Lower 95.0% Upper 95.0%


-0.003989629 0.058473126
0.925768224 2.484448004
-0.520085138 2.594739534
-3.700161253 -1.161887345

Return Data
Date
5/3/2004
6/1/2004
7/1/2004
8/2/2004
9/1/2004
10/1/2004
11/1/2004
12/1/2004
1/3/2005
2/1/2005
3/1/2005
4/1/2005
5/2/2005
6/1/2005
7/1/2005
8/1/2005
9/1/2005
10/3/2005
11/1/2005
12/1/2005
1/3/2006
2/1/2006
3/1/2006
4/3/2006
5/1/2006
6/1/2006
7/3/2006
8/1/2006
9/1/2006
10/2/2006
11/1/2006
12/1/2006
1/3/2007
2/1/2007
3/1/2007
4/2/2007
5/1/2007
6/1/2007
7/2/2007

Amazon.com
$
48.50
$
54.40
$
38.92
$
38.14
$
40.86
$
34.13
$
39.68
$
44.29
$
43.22
$
35.18
$
34.27
$
32.36
$
35.51
$
33.09
$
45.15
$
42.70
$
45.30
$
39.86
$
48.46
$
47.15
$
44.82
$
37.44
$
36.53
$
35.21
$
34.61
$
38.68
$
26.89
$
30.83
$
32.12
$
38.09
$
40.34
$
39.46
$
37.67
$
39.14
$
39.79
$
61.33
$
69.14
$
68.41
$
78.54

Amazon
return
12.16%
-28.46%
-2.00%
7.13%
-16.47%
16.26%
11.62%
-2.42%
-18.60%
-2.59%
-5.57%
9.73%
-6.81%
36.45%
-5.43%
6.09%
-12.01%
21.58%
-2.70%
-4.94%
-16.47%
-2.43%
-3.61%
-1.70%
11.76%
-30.48%
14.65%
4.18%
18.59%
5.91%
-2.18%
-4.54%
3.90%
1.66%
54.13%
12.73%
-1.06%
14.81%

Mkt - Rf
0.0208
-0.0387
0.0016
0.0195
0.0167
0.0467
0.0336
-0.0282
0.0211
-0.019
-0.0273
0.0355
0.0092
0.0409
-0.0089
0.0077
-0.0235
0.0373
0.0003
0.0366
-0.005
0.0154
0.0094
-0.0353
-0.0044
-0.0059
0.0209
0.0154
0.033
0.0195
0.0068
0.015
-0.0178
0.0086
0.0355
0.0348
-0.0188
-0.0358

SMB
0.0225
-0.0382
-0.0156
0.0282
0.0049
0.0411
0.0018
-0.0167
-0.0076
-0.0137
-0.0395
0.0301
0.0258
0.0277
-0.0088
-0.0064
-0.0105
0.0098
-0.0047
0.0532
-0.0031
0.0351
-0.0122
-0.03
-0.0047
-0.039
0.008
-0.0121
0.0168
0.007
-0.0093
0.0002
0.0138
-0.002
-0.0206
-0.0005
0.0069
-0.0274

8/1/2007
9/4/2007
10/1/2007
11/1/2007
12/3/2007
1/2/2008
2/1/2008
3/3/2008
4/1/2008
5/1/2008
6/2/2008
7/1/2008
8/1/2008
9/2/2008
10/1/2008
11/3/2008
12/1/2008
1/2/2009
2/2/2009
3/2/2009
4/1/2009

$
$
$
$
$
$
$
$
$
$
$
$
$
$
$
$
$
$
$
$
$

79.91
93.15
89.15
90.56
92.64
77.70
64.47
71.30
78.63
81.62
73.33
76.34
80.81
72.76
57.24
42.70
51.28
58.82
64.79
73.44
80.52

1.74%
16.57%
-4.29%
1.58%
2.30%
-16.13%
-17.03%
10.59%
10.28%
3.80%
-10.16%
4.10%
5.86%
-9.96%
-21.33%
-25.40%
20.09%
14.70%
10.15%
13.35%
9.64%

0.0074
0.0377
0.0226
-0.0527
-0.007
-0.0644
-0.0233
-0.0122
0.0495
0.0221
-0.0803
-0.0147
0.0098
-0.0996
-0.1855
-0.0854
0.0206
-0.0774
-0.1011
0.0876
0.1104

-0.0009
-0.0247
0.0007
-0.0272
0.0006
-0.0076
-0.0067
0.0087
-0.016
0.028
0.0091
0.0389
0.0366
-0.002
-0.0205
-0.0346
0.0404
-0.0101
-0.0047
0.0074
0.0505

HML
0.0172
0.0442
0.0113
0.004
-0.0095
0.0196
-0.0035
0.0252
0.0285
0.0171
-0.0049
-0.0116
0.0284
-0.0047
0.0144
0.0122
-0.0074
-0.0175
0.0051
0.0118
-0.0076
0.0004
0.0307
0.0275
0.0151
0.0325
-0.0166
-0.0049
0.0049
0.0039
0.0256
0
0.0032
0.0031
-0.0108
-0.0023
-0.0107
-0.0301

-0.0242
-0.021
-0.0197
-0.0088
-0.0002
0.0313
0.0004
0.0026
0.0008
-0.003
-0.0093
0.0357
0.0165
0.0437
-0.0314
-0.0509
-0.012
-0.0994
-0.0673
0.0271
0.0586

Chapter 12 - Master it!


The Fama-French three-factor model has become a popular APT model. However, another model called the Carhart four-factor model has also been proposed (Carhart,
Mark, 1997, "On Persistence in Mutual Fund Performance", Journal of Finance, vol. 52, no. 1, p. 57-82). In the four-factor model, the first three factors are the same as the
Fama-French three-factor model. The fourth factor in the model is momentum. The momentum factor is constructed by
the monthly return difference between the returns on the high and low prior return portfolios, to capture the cross-sectional return patterns.
The factors for the four-factor model are available on Kenneth French's website (http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/index.html). Note, there is a
file for the three-factor model as well as a separate file for the momentum factor.
Kenneth French's website

a.

The data files are in a zip format. You will need to open the Zip file, save the text file, and then open the text file in Excel. Make sure you download the monthly factors.
The Text Import Wizard in Excel will walk you through the steps necessary to import the text files into columns. When you get the data table set up, estimate the fourfactor model for the stock and mutual fund you have chosen and answer the following questions for the stock and mutual fund you selected in the previous chapter.

1) Would you expect the explanatory power of the four-factor regression to be higher or lower than the market model regression from the previous chapter? Why?
2) Are the alpha and beta for each regression statistically different from zero?
3) How do you interpret the betas for each independent variable for the stock and the mutual fund?
4) Which of the two regression estimates has the highest R squared? Is this what you would have expected? Why?

Master it! Solution


a.

Month/Year

Stock price
IBM

Mutual fund
price
FMAGX
IBM

FMAGX

Mkt - Rf

SMB

HML

Momentum

Você também pode gostar