http://www.bionicturtle.

com/forum/viewthread/599/
Inputs/assumptions
Matrix math
Key portfolio calculations (marginal VaR, Inc'l VaR, Component VaR)
Portfolio inputs:
Position
Volatility
Tot Portfolio
Correlation

A

Var-Covar
Matrix:

B
$100.00
10.00%
$200.00
0.20

$100.00
14.00%

0.01
0

0
0.02

Portfolio
Variance (matrix)
Variance (alt)
Volatility
Volatility (alt.)
VaR

$352.00
$352.00
$18.76
$18.76
$43.65

Individual Positions
Positions
Volatility
(sigma)(X)
Individual VaR
Beta
Marginal VaR
Marginal VaR

A

Incremental Position
+/- Position
(x Marg'l VaR)
Incremetal VaR

A

Component VaR
Percent Contrib.

B
$100.00
10.00%
1.28
$23.26
0.727
0.159
0.159

$100.00
14.00%
2.24
$32.57
1.273
0.278
0.278
B

$0.010
0.00159
0.00159

$0.000
0.0000
0.00000

$15.87
36%

$27.77
64%

Confidence
Critical z

99.00%
2.33

Matrix math:
Positions (x')
Var-Covar Matrix (sigma)
Positions (x)
$100.00
$100.00
0.01
0
$100.00
0
0.02
$100.00

Positions (x')
(sigma)(x)
x'(sigma)x
$100.00
$100.00
1.28
$352.00
2.24

1.28
2.24

1.28
2.24

Question:
Assume a $200 t
has volatility of 1
(i) What is portfo
(ii) What is portfo
(iii) What are the
(iv) What is the i
(v) What are the
(vi) If correlation
Answer:

(i)
Kudos if you can
Variance = ($100
Volatility = SQRT
Or, you can use
Volatility = SQRT
(9.38%)($200) =

(ii)
No difference!
With 99%, the no
Diversified VaR =
This is a relative

(iii)
($100)(10%)(2.3
($100)(14%)(2.3

(iv)
The incremental
Assuming the ma
approximate incr
But please note
between Portfolio
$43.65

(v)
First, we want th
But, given that th
Marginal VaR = P
Asset #1 Margin
Asset #2 Margin
Component VaR
Asset #1 Compo
Asset #2 Compo
Percentage contr
Asset #1 Compo
Asset #2 Compo

(vi)
If correlation = 1
But for imperfect

Component VaR
Asset #1 Compo
Asset #2 Compo
Percentage contr
Asset #1 Compo
Asset #2 Compo

(vi)
If correlation = 1
But for imperfect
Sum of compone

Question:
Assume a $200 two-asset portfolio with equal positions in both assets ($100 + $100). Asset #1 has vo
has volatility of 14%. Their correlation is 20%. Our desired confidence is 99%.
(i) What is portfolio volatility?
(ii) What is portfolio VaR and diversified VaR and what is the difference?
(iii) What are the individual VaRs?
(iv) What is the incremental VaR?
(v) What are the component VaRs and percentage contributions?
(vi) If correlation is perfect (1.0), how will portfolio VaR compare to individual VaRs?
Answer:
(i)
Kudos if you can use matrix math to derive (see XLS). But also,
Variance = ($100^2)(10%^2)+($100^2)(14%^2)+(2)($100)($100)(0.20)(10%)(14%) = 352
Volatility = SQRT(352) = $18.8
Or, you can use percentage weights instead of dollar positions:
Volatility = SQRT[(50%^2)(10%^2)+(50%^2)(14%^2)+(2)(50%)(50%)(0.20)(10%)(14%)] = 9.38%
(9.38%)($200) = $18.8

(ii)
No difference!
With 99%, the normal deviate = NORMSINV(99%) = 2.33
Diversified VaR = (2.33)($18.8) = $43.6
This is a relative VaR. No expected returns are given and expected return is not netted, which would b
(iii)
($100)(10%)(2.33) = $23.26, and
($100)(14%)(2.33) = $32.57

(iv)
The incremental VaR can be approximated with: marginal VaR * trade.
Assuming the marginal VaR = 0.159 (see next), and the trade is +$10, then
approximate incremental VaR = (10)(0.159) = $1.59
But please note that using the marginal VaR is only an approximation. The true incremental VaR is giv
between Portfolio VaR (before trade) - Portfolio VaR (after trade)
(v)
First, we want the marginal VaR. Note in XLS we can get this two ways.
But, given that the betas are, respectively, 0.727 and 1.273,
Marginal VaR = Portfolio VaR/Portfolio Value * beta. In this case,
Asset #1 Marginal VaR = $43.6/$200 * 0.727 beta = 0.159
Asset #2 Marginal VaR = $43.6/$200 * 1.273 beta = 0.278
Component VaR = Position * Marginal VaR. In this case,
Asset #1 Component VaR = (0.159)($100) = $15.87
Asset #2 Component VaR = (0.278)($100) = $27.77
Percentage contributions are:
Asset #1 Component VaR % = $15.87/$43.6 = 36%
Asset #2 Component VaR = $27.77/43.6 = 64%
(vi)
If correlation = 1.0, sum of individual VaRs will EQUAL portfolio VaR.
But for imperfect correlation (rho < 1), sum of individual VaRs will be GREATER THAN portfolio VaR.

Component VaR = Position * Marginal VaR. In this case,
Asset #1 Component VaR = (0.159)($100) = $15.87
Asset #2 Component VaR = (0.278)($100) = $27.77
Percentage contributions are:
Asset #1 Component VaR % = $15.87/$43.6 = 36%
Asset #2 Component VaR = $27.77/43.6 = 64%
(vi)
If correlation = 1.0, sum of individual VaRs will EQUAL portfolio VaR.
But for imperfect correlation (rho < 1), sum of individual VaRs will be GREATER THAN portfolio VaR.
Sum of component VaRs, by definition, will be EQUAL to portfolio VaR.

100). Asset #1 has volatility of 10%, Asset #2

s?

14%) = 352

%)(14%)] = 9.38%

etted, which would be an absolute VaR.

ncremental VaR is given by the difference

HAN portfolio VaR.

HAN portfolio VaR.

Mean
Std Dev
Skew
Kurt

A
0.61%
0.02%
1.00%
1.55%
1.94%
1.85%
0.13%
0.82%
0.75%
2.05%
0.60%
0.82%
-3.70%
2.17%
1.24%
-0.83%
-1.00%
-1.11%
1.57%
-1.66%
-0.29%
0.77%
0.54%
-1.43%
-0.83%
-5.75%
-5.61%
-1.44%
-0.06%
2.21%
0.48%
-0.52%
1.62%
2.27%
0.31%
1.54%

B
0.20%
0.58%
1.45%
1.73%
1.87%
0.58%
0.52%
0.55%
1.30%
0.63%
0.76%
1.12%
-1.72%
2.22%
2.37%
0.17%
0.15%
-1.85%
1.45%
-0.81%
-0.10%
0.88%
0.32%
-2.26%
-0.73%
-2.44%
-5.37%
-1.88%
0.63%
0.00%
-1.08%
0.19%
0.14%
1.37%
0.28%
1.30%

C
0.24%
-0.30%
1.15%
1.76%
1.70%
0.54%
0.46%
0.53%
0.95%
1.15%
0.53%
0.33%
-1.67%
1.76%
1.91%
-0.55%
0.41%
-1.69%
1.44%
-1.84%
0.24%
1.28%
0.73%
-3.08%
-1.89%
-2.25%
-4.22%
-1.58%
0.26%
-0.37%
-0.79%
-0.26%
0.51%
1.80%
-0.38%
1.16%

D
0.64%
0.40%
2.15%
0.99%
0.89%
1.53%
0.30%
0.04%
1.13%
1.27%
0.60%
1.04%
-1.78%
3.09%
2.38%
1.02%
0.91%
-0.26%
2.76%
-1.07%
0.26%
1.74%
0.93%
-1.66%
0.12%
-3.18%
-1.48%
1.85%
-0.14%
2.43%
0.70%
-0.04%
-0.30%
2.10%
0.35%
0.28%

Port
0.42%
0.18%
1.44%
1.51%
1.60%
1.12%
0.35%
0.48%
1.03%
1.27%
0.62%
0.83%
-2.22%
2.31%
1.98%
-0.05%
0.12%
-1.23%
1.80%
-1.35%
0.03%
1.17%
0.63%
-2.11%
-0.83%
-3.41%
-4.17%
-0.76%
0.17%
1.07%
-0.17%
-0.15%
0.49%
1.88%
0.14%
1.07%

0.07%
1.94%
-1.60
2.86

0.13%
1.54%
-1.48
3.39

0.00%
1.47%
-0.97
0.67

0.61%
1.34%
-0.60
0.82

0.20%
1.46%
-1.27
1.73

VarCovarMat
0.000365 0.000246 0.000233 0.000198

0.000246 0.000231 0.000208 0.000140
0.000233 0.000208 0.000210 0.000138
0.000198 0.000140 0.000138 0.000175
CorrelMat
1.00000
0.84911
0.83976
0.78304
Weights
Position

Port Mean
Port Vol
Port Vol
Variance
Port VaR ( Raw )
Port VaR ( Rel )
Vol (Pop)
Vol (Sample )
Sigma (x)
CL
Z-Score
CF Mod

25%
100
Sample
0.20%
1.46%
5.8324
34.017
13.568

1.91%
1.94%
0.1

0.84911
1.00000
0.94580
0.69716
25%
100

0.83976
0.94580
1.00000
0.72100
25%
100

0.78304
0.69716
0.72100
1.00000
25%
100

Total
100%
400

Population

TRUE

1.44%
5.7508
33.07
13.38

5.8324
13.568
-3.1900%

1.52%
1.54%
0.08

1.45%
1.47%
0.08

1.32%
1.34%
0.07

99.00%
2.33
0.73

Individual VaR
Slope
Beta
Marginal VaR
Marginal VaR

4.5057
1.26
1.26
0.0427
0.0427

3.5838
1.00
1.00
0.0339
0.0339

3.4211
0.95
0.95
0.0324
0.0324

3.1205
0.79
0.79
0.0267
0.0267

0.13568
0.13568

Component VaR

4.2722
31%

3.3864
25%

3.2386
24%

2.6710
20%

13.568
TRUE

33%
133.333
5.6963

33%
133.333
4.5153

33%
133.333
4.3181

0%
0
0.0000

100%
400
14.530
-3.4304%

New Weights
Increment
Incremetal VaR

0

0

0

0

Modified
0.00069

0.00039

0.00041

0
0
0

0
0
0

0
0
0

0
0
0

0.00039
0.00041
0.00034

0.00049
0.00034
0.00022

0.00034
0.00031
0.00027

1.00000
0.84911
0.83976
0.78304

0.84911
1.00000
0.94580
0.69716

0.83976
0.94580
1.00000
0.72100

0.78304
0.69716
0.72100
1.00000

Modified
1.0000
0.6749
0.8796
0.8141

0.6749
1.0000
0.8778
0.6282

0.8796
0.8778
1.0000
0.9519

Sample

Population

1.92%
7.6695
58.821
17.84 17.84182
-4.2584% -4.2584%
1.91%
1.94%
TRUE

1.52%
1.54%
TRUE

1.45%
1.47%
TRUE

1.32%
1.34%
TRUE

Modified Beta

1.89%
7.5622
57.187
17.592

2.63%
2.67%
0.18

2.21%
2.24%
0.14

1.77%
1.80%
0.13

0.8819
6.2138
6.2138

1.0544
5.2082
5.2082

0.5160
4.1799
4.1799

1.29
0.0574
0.0574

1.01
0.0451
0.0451

0.94
0.0417
0.0417

5.7420
32%

4.5098
25%

4.1749
23%

33%
133.333
7.6560

33%
133.333
6.0131

33%
133.333
5.5666

0.00034

0.00022
0.00027
0.00026

0.8141
0.6282
0.9519
1.0000

1.60%
1.63%
0.11

0.4960
3.7857
3.7857
0.77
0.0342
0.0342

0.178418
0.178418

3.4151
19%

17.84182

0%
0.000
0.0000

100%
400
19.2357
-4.6069%