Anon

Regression Models with Categorical Variables 133

We use the S&P 500 as a proxy for the market returns and the 90-day
Treasury rate as a proxy for the risk-free rate. The data are presented in
Table 6.3, which shows each observation for the variable Dtxt. The regres-
sion results for the two mutual funds are as follows:

Coefficient

Coefficient

Estimate

Standard

Error t-Statistic p-Value

Fund A

α –0.23 0.10 –2.36 0.0198

β 1   0.75 0.03 25.83 4E-50

β 2   0.18 0.04   4.29 4E-05

Fund B

α   0.00 0.14 –0.03 0.9762

β 1   0.75 0.04 18.02 2E-35

β 2   0.13 0.06   2.14 0.0344

tAble 6.3 Data for Estimating Mutual Fund Characteristic Line with a
Dummy Variable
Mutual Fund
Month
Ended rM rft

Dummy

Dt

rM – rft =

xt Dtxt

A

rt

B

rt

A

yt

B
yt
01/31/1995 2.60 0.42 0 2.18 0 0.65 1.28 0.23 0.86
02/28/1995 3.88 0.40 0 3.48 0 3.44 3.16 3.04 2.76
03/31/1995 2.96 0.46 1 2.50 2.5 2.89 2.58 2.43 2.12
04/30/1995 2.91 0.44 1 2.47 2.47 1.65 1.81 1.21 1.37
05/31/1995 3.95 0.54 1 3.41 3.41 2.66 2.96 2.12 2.42
06/30/1995 2.35 0.47 1 1.88 1.88 2.12 2.18 1.65 1.71
07/31/1995 3.33 0.45 1 2.88 2.88 3.64 3.28 3.19 2.83
08/31/1995 0.27 0.47 1 –0.20 –0.2 –0.40 0.98 –0.87 0.51
09/30/1995 4.19 0.43 1 3.76 3.76 3.06 3.47 2.63 3.04
10/31/1995 –0.35 0.47 1 –0.82 –0.82 –1.77 –0.63 –2.24 –1.10
11/30/1995 4.40 0.42 1 3.98 3.98 4.01 3.92 3.59 3.50
12/31/1995 1.85 0.49 1 1.36 1.36 1.29 1.73 0.80 1.24
01/31/1996 3.44 0.43 1 3.01 3.01 3.36 2.14 2.93 1.71
02/29/1996 0.96 0.39 1 0.57 0.57 1.53 1.88 1.14 1.49
03/31/1996 0.96 0.39 1 0.57 0.57 0.59 1.65 0.20 1.26
04/30/1996 1.47 0.46 1 1.01 1.01 1.46 1.83 1.00 1.37
05/31/1996 2.58 0.42 1 2.16 2.16 2.17 2.20 1.75 1.78
06/30/1996 0.41 0.40 1 0.01 0.01 –0.63 0.00 –1.03 –0.40

(continued)

The adjusted R^2 is 0.93 and 0.83 for mutual funds A and B, respectively.