Scribd
Upload
11 views

Revisiting Measures of Risk

Revisiting measures of risk

Uploaded by

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

Revisiting Measures of Risk

Revisiting measures of risk

Uploaded by

singhashwini
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

2/3/2017

BASIC MEASURES OF RISK

WHAT WILL YOU LEARN?

Types of risk
Basic measures of risk

1
2/3/2017

TYPES OF RISK

Business cycle Volatility


Credit Political
Default Market
Interest rate Legal
Exchange rate Operational
Liquidity

HOW DO WE MEASURE RISK?

The most common measure of risk is volatility of


returns.
Volatilityis measured by the standard deviation σ of
a return distribution.

2
2/3/2017

VOLATILITY

Given a sample of N returns,

EXAMPLE: RUSSELL 3000 QUARTERLY RETURNS


R3000 Quarterly return Deviation from the ±σ
% mean
March 2003 -24.66 -37.48 No
June 2003 0.77 -12.05 Yes
September 2003 25.92 13.11 Yes
December 2003 31.06 18.25 No
March 2004 38.19 25.38 No
June 2004 20.46 7.65 Yes
September 2004 14.26 1.45 Yes
December 2004 11.95 -0.87 Yes
March 2005 7.09 -5.73 Yes
June 2005 8.05 -4.77 Yes
September 2005 14.57 1.76 Yes
December 2005 6.12 -6.70 Yes

Mean 12.82%
Population std. dev. 15.45%
Sample std. dev. 18.13%
Source: Russell research database

3
2/3/2017

ANNUALIZING VOLATILITY

SUMMARY

A common measure of risk is the volatility of


returns, measured as the standard deviation of the
return distribution.

4
2/3/2017

MEASURING BAD VARIATION

WHAT WILL YOU LEARN?

Target semivariance
Downside risk

1
2/3/2017

WHAT IS SEMIVARIANCE?

Semivariance is computed by squaring only negative


deviations from the mean.
The square root of semivariance is called
semideviation.

TARGET SEMIVARIANCE

Suppose you have a return target, or a minimal


acceptable return (MAR).
Target semivariance is the expected squared
deviations below the target.
Target semideviation is the square root of target
semivariance.
Target semideviation is a measure of downside risk.

2
2/3/2017

LOWER PARTIAL MOMENTS (LPM)

Target semideviation is a special case of lower


partial moments (LPM) methodology for dealing
with downside variation.
Formula for a lower partial moment of degree p

EXAMPLE: RUSSELL TOP 50 INDEX QUARTERLY


DOWNSIDE SEMIVARIANCE

Quarter Return % d(i) Deviation


200109 -13.39 1 -13.39
200112 8.98 0 8.98
200203 -1.69 1 -1.69
200206 -16.40 1 -16.40
200209 -15.93 1 -15.93
200212 10.55 0 10.55
200303 -2.52 1 -2.52
200306 13.95 0 13.95
200309 1.16 0 1.16
200312 10.17 0 10.17
200403 -0.57 1 -0.57
200406 1.04 0 1.04

Tau 0

Mean Squared deviation = target semivariance 59.2957


Target semideviation 7.700
Source: Russell research database

3
2/3/2017

UPSIDE SEMIDEVIATION

Upside risk – upside semideviation – is the converse


of downside deviation.

SUMMARY

A common measure of risk is the volatility of


returns, measured as the standard deviation of the
return distribution.
Downside semivariance is a special case of the LPM
methodology with power p = 2 and target equal to
the mean.
Downside deviation is useful when comparing
distributions that are not normal and have different
means.

4
2/3/2017

TRACKING ERROR AND RESIDUAL RISK

WHAT WILL YOU LEARN?

Tracking error
Residual risk

1
2/3/2017

TRACKING ERROR

Tracking error is the standard deviation of the


arithmetic excess return.

RESIDUAL RISK

2
2/3/2017

TRACKING ERROR VS. RESIDUAL RISK

When beta is equal to 1, the tracking error and the


residual risk are equal.
When beta is not equal to 1, the tracking error and
the residual risk differ from each other.

SUMMARY

Tracking error and residual risk


When alpha equals the arithmetic excess return,
residual risk equals tracking error.

You might also like