Professional Documents
Culture Documents
MIT15 401F08 Lec12
MIT15 401F08 Lec12
401
Andrew W. Lo
Harris & Harris Group Professor, MIT Sloan School
© 2007–2008 by Andrew W. Lo
Critical Concepts 15.401
Motivation
Statistical Background
Empirical Properties of Stock Returns
Anomalies
Readings
Brealey, Myers, and Allen Chapters 7, 24.1, 24.4
Terminology
Terminology
Mean, variance, standard deviation:
Sample estimators:
Other Statistics
Median
– 50th percentile (probability of 1/2 that Rt < median)
Skewness
– Is the distribution symmetric?
– Negative: big losses are more likely than big gains
– Positive: big gains are more likely than big losses
Correlation
– How closely do two variables move together?
-5 -4 -3 -2 -1 0 1 2 3 4 5
2
1
1
0
0 -4 -3 -2 -1 0 1 2 3 4
-4 -3 -2 -1 0 1 2 3 4 -1
-1
-2
-2
-3 -3
-4 -4
4 3
ρ = .8 3
ρ = –.5 2
2
1
1
0
0 -4 -3 -2 -1 0 1 2 3 4
-4 -3 -2 -1 0 1 2 3 4 -1
-1
-2
-2
-3 -3
-4 -4
Normal Distribution
Bell-shaped, symmetric
A model of randomness
Central Limit Theorem
Confidence Intervals
-5 -4 -3 -2 -1 0 1 2 3 4 5
If R is normally distributed, then …
68% of observations fall within +/–1.00 std. deviations from mean
90% of observations fall within +/–1.65 std. deviations from mean
95% of observations fall within +/–1.96 std. deviations from mean
99% of observations fall within +/–2.58 std. deviations from mean
GM Monthly Returns
0.21
0.14
0.07
0.00
-21% -15% -9% -3% 3% 9% 15% 21%
70
60
50
40
30
20
75
70
65
60
55
50
0 10 20 30 40 50 60 70 80 90 100
1000
100
10
0.1
Dec-45 Dec-53 Dec-61 Dec-69 Dec-77 Dec-85 Dec-93 Dec-01
12%
9%
6%
3%
0%
Jun-53 Jan-63 Jun-72 Jan-82 Jun-91 Jan-01
20%
15%
10%
5%
0%
-5%
-10%
-15%
-20%
-25%
1.0%
0.0%
-2.5% -1.5% -0.5% 0.5% 1.5% 2.5%
-1.0%
-2.0%
Scatterplot, S&P 500 This Month vs. Last Month, 1926 to 1997
20%
15%
10%
5%
0%
-25% -15% -5% 5% 15% 25%
-5%
-10%
-15%
-20%
17%
8%
0%
-35% -25% -15% -5% 5% 15% 25% 35%
-8%
-17%
-25%
5%
4%
3%
2%
1%
0%
Jan 26 Jan 36 Jan 46 Jan 56 Jan 66 Jan 76 Jan 86 Jan 96
16.0
14.0
12.0
10.0
8.0
Small 2 3 4 5 6 7 8 9 Big
Firms sorted by MARKET CAPITALIZATION
9%
8% All Months Januarys
7%
6%
5%
4%
3%
2%
1%
0%
Small 2 3 4 5 6 7 8 9 Big
Firm s sorted by MARKET CAPITALIZATION
18%
16%
14%
12%
10%
8%
Low 2 3 4 5 6 7 8 9 High
Firms sorted by PRICE / BOOK EQUITY
18%
15%
12%
9%
6%
3%
Low 2 3 4 5 6 7 8 9 High
Firms sorted by PAST 12-MONTH RETURN
15.0
13.0
11.0
9.0
7.0
5.0
3.0
Low 2 3 4 5 6 7 8 9 High
Firms sorted by last year's OPERATING ACCRUALS
*Operating income minus operating cashflows
14.1% 14.3%
16% 13.3%
11.3%
12%
11.6%
6.1%
8%
4% 5.0%
3.6% 4.0%
1.6% Non-issuers
IPOs
0%
1st year 2nd year 3rd year 4th year 5th year
17.7% 17.4%
20%
16.2%
12.9% 12.3%
15%
11.8%
10%
9.1%
7.5%
6.6%
5%
Non-issuers
0.3% SEOs
0%
1st year 2nd year 3rd year 4th year 5th year
40%
Cumulative average abnormal returns
30%
20%
10%
0%
-10%
-126 -105 -84 -63 -42 -21 0 21 42 63 84 105 126 147 168 189 210 231 252
36
32
28
24
# Frequency
20
16
12
0
-3 -2 -1 0 1 2
Midpoint
Estimates of individual mutual-fund alphas 1972 to 1991. The frequency distribution
of estimated alphas for all equity mutual funds with 10-year continuous records.
Image by MIT OpenCourseWare.
Observations
The average annual return on U.S. stocks from 1926 – 2004 was 11.2%.
The average risk premium was 7.8%.
Stocks are quite risky. The standard deviation of returns for the overall
market is 4.5% monthly (16.4% annually).
Individual stocks are much riskier. The average monthly standard
deviation of an individual stock is around 17% (or 50% annually).
Stocks tend to move together over time: when one stock goes up, other
stocks are likely to go up as well. The correlation is far from perfect.
Stock returns are nearly unpredictable. For example, knowing how a stock
does this month tells you very little about what will happen next month.
Market volatility changes over time. Prices are sometimes quite volatile.
The standard deviation of monthly returns varies from roughly 2% to 20%.
Financial ratios like DY and P/E ratios vary widely over time. DY hit a
maximum of 13.8% in 1932 and a minimum of 1.17% in 1999. The P/E ratio
hit a maximum of 33.4 in 1999 and a minimum of 5.3 in 1917.
Anomalies:
Size Effect: Smaller stocks typically outperform larger stocks,
especially in January.
January Effect: Returns in January tend to be abnormally high.
Value Effect: Low P/B (value) stocks typically outperform high P/B
(growth) stocks.
Momentum: Stocks with high returns over the past 12 months
typically continue to outperform stocks with low past returns.
Accruals and Issuances: Stocks with high past accruals and/or
recent stock offerings typically underperform stocks with low past
accruals and no stock offerings.
Lefevre, E., 2006, Reminiscences of a Stock Operator. New York: John Wiley & Sons.
Malkiel, B., 1996, A Random Walk Down Wall Street: Including a Life-Cycle Guide to Personal
Investing. New York: W.W. Norton.
For information about citing these materials or our Terms of Use, visit: http://ocw.mit.edu/terms.