Documente Academic
Documente Profesional
Documente Cultură
2/9/2015
Expected Values:
Discrete Random Variables
Sums of Random Variables
Discrete variables
can assume only a countable number of different
values
gaps between values along the number line
It is possible to list all X values and the associated
P(X) in Probability Distributions
Random variables
Actual outcomes are determined by chance.
Notation:
X outcome
P(X) probability of an outcome
X fi / fi = fi/n X P(X)
0 0.56 0 0.56
1 0.13 1 0.13
2 0.07 2 0.07
3 0.07 3 0.07
4 0.04 4 0.04
5 0.13 5 0.13
Whatis the expected number of drinks
consumed per occasion by light-drinking E370
students? = ( )
X P(X) Products Sum
0 0.56 =0*0.56 = 0 0
1 0.13 =1*0.13 = 0.13 +0.13
2 0.07 =2*0.07 = 0.14 +0.14
3 0.07 =3*0.07 = 0.21 +0.21
4 0.04 =4*0.04 = 0.16 +0.16
5 0.13 =5*0.13 = 0.65 +0.65 = 1.29
Expected Values
Whatis the expected number of drinks
consumed per occasion by light-drinking E370
students? = ( )
X P(X) Products Sum
0 0.56 =0*0.56 = 0 0
1 0.13 =1*0.13 = 0.13 +0.13
2 0.07 =2*0.07 = 0.14 +0.14
3 0.07 =3*0.07 = 0.21 +0.21
4 0.04 =4*0.04 = 0.16 +0.16
5 0.13 =5*0.13 = 0.65 +0.65 = 1.29
Expected Values
Whatis the expected number of drinks
consumed per occasion by light-drinking E370
students? = ( )
X P(X) Products Sum
0 0.56 =0*0.56 = 0 0
1 0.13 =1*0.13 = 0.13 +0.13
2 0.07 =2*0.07 = 0.14 +0.14
3 0.07 =3*0.07 = 0.21 +0.21
4 0.04 =4*0.04 = 0.16 +0.16
5 0.13 =5*0.13 = 0.65 +0.65 = 1.29
Expected Values
What is the expected variance of the number of
drinks consumed per occasion by light-drinking
E370 students? = () ( )
X P(X) (X-E(X)) (X-E(X))2 (X-E(X))2*P(X)
0 0.56 (0-1.29) (0-1.29)2 (0-1.29)2*0.56 0.931896
1 0.13 (1-1.29) (1-1.29)2 (1-1.29)2*0.13 + 0.010933
2 0.07 (2-1.29) (2-1.29)2 (2-1.29)2*0.07 + 0.035287
3 0.07 (3-1.29) (3-1.29)2 (3-1.29)2*0.07 + 0.204687
4 0.04 (4-1.29) (4-1.29)2 (4-1.29)2*0.04 + 0.293764
+ 1.789333
5 0.13 (5-1.29) (5-1.29)2 (5-1.29)2*0.13
= 3.27
= () ( )
Loss
% Loss P(Loss) (Xi)*P(Xi) (XiiE(X))22 *P(Xii)
Value
(10000-285)
(10000-285)22*0.001
*0.001
Total loss 10000 0.001 10 =94381.23
=94381.23
50% loss 5000 0.010 50 222312.3
222312.3
25% loss 2500 0.050 125 245311.3
245311.3
10% loss 1000 0.100 100 51122.5
51122.5
0% loss 0 0.839 0 68147.78
68147.78 SQRT
E(X) $285 V(X)
V(X) =
= 681275
681275 $825.40
Loss
% Loss P(Loss) (Xi)*P(Xi) (XiiE(X))22 *P(Xii)
Value
(10000-285)
(10000-285)22*0.001
*0.001
Total loss 10000 0.001 10 =94381.23
=94381.23
50% loss 5000 0.010 50 222312.3
222312.3
25% loss 2500 0.050 125 245311.3
245311.3
10% loss 1000 0.100 100 51122.5
51122.5
0% loss 0 0.839 0 68147.78
68147.78 SQRT
E(X) $285 V(X)
V(X) =
= 681275
681275 $825.40
Loss
% Loss P(Loss) (Xi)*P(Xi) (XiiE(X))22 *P(Xii)
Value
(10000-285)
(10000-285)22*0.001
*0.001
Total loss 10000 0.001 10 =94381.23
=94381.23
50% loss 5000 0.010 50 222312.3
222312.3
25% loss 2500 0.050 125 245311.3
245311.3
10% loss 1000 0.100 100 51122.5
51122.5
0% loss 0 0.839 0 68147.78
68147.78 SQRT
E(X) $285 V(X)
V(X) =
= 681275
681275 $825.40
Loss
% Loss P(Loss) (Xi)*P(Xi) (XiiE(X))22 *P(Xii)
Value
(10000-285)
(10000-285)22*0.001
*0.001
Total loss 10000 0.001 10 =94381.23
=94381.23
50% loss 5000 0.010 50 222312.3
222312.3
25% loss 2500 0.050 125 245311.3
245311.3
10% loss 1000 0.100 100 51122.5
51122.5
0% loss 0 0.839 0 68147.78
68147.78 SQRT
E(X) $285 V(X)
V(X) =
= 681275
681275 $825.40
Loss
% Loss P(Loss) (Xi)*P(Xi) (XiiE(X))22 *P(Xii)
Value
(10000-285)
(10000-285)22*0.001
*0.001
Total loss 10000 0.001 10 =94381.23
=94381.23
50% loss 5000 0.010 50 222312.3
222312.3
25% loss 2500 0.050 125 245311.3
245311.3
10% loss 1000 0.100 100 51122.5
51122.5
0% loss 0 0.839 0 68147.78
68147.78 SQRT
E(X) $285 V(X)
V(X) =
= 681275
681275 $825.40
Loss
% Loss P(Loss) (Xi)*P(Xi) (XiiE(X))22 *P(Xii)
Value
(10000-285)
(10000-285)22*0.001
*0.001
Total loss 10000 0.001 10 =94381.23
=94381.23
50% loss 5000 0.010 50 222312.3
222312.3
25% loss 2500 0.050 125 245311.3
245311.3
10% loss 1000 0.100 100 51122.5
51122.5
0% loss 0 0.839 0 68147.78
68147.78 SQRT
E(X) $285 V(X)V(X)
= 681275.11
= 681275 $825.40
Loss
% Loss P(Loss) (Xi)*P(Xi) (XiiE(X))22 *P(Xii)
Value
(10000-285)
(10000-285)22*0.001
*0.001
Total loss 10000 0.001 10 =94381.23
=94381.23
50% loss 5000 0.010 50 222312.3
222312.3
25% loss 2500 0.050 125 245311.3
245311.3
10% loss 1000 0.100 100 51122.5
51122.5
0% loss 0 0.839 0 68147.78
68147.78 SQRT
E(X) $285 V(X)V(X)
= 681275.11
= 681275 $825.40
Summary
The president of Midwest Foods is thinking of
building a meat distribution facility on the
outskirts of Chicago. Contribution per pound to
profits is known to be $0.40 for pork and $0.50
for beef. The president is interested in overall
profits. Define a relevant random variable.
TP = 0.4*P + 0.5*B
A practical problem
Itis known that expected pork sales per
month are 2300 pounds. Expected beef sales
per month are 4200. Calculate the expected
value of profits.
E(TP) = E(0.4P + 0.5B)
= E(0.4P) + E(0.5B)
= 0.4*E(P) + 0.5*E(B)
= 0.4*2300 + 0.5*4200
= 920 + 2100 = $3,020
Expected Value
The expected value of the sum of random
variables is the sum of the expected values
of its parts.
For S= aX + bY + c
E(S) =E(aX + bY + c)
=E(aX) + E(bY) + (E(c))
=a*E(X) + b*E(Y) + c
(E(c) = c)
Big News
Theexpected standard deviation of pork
sales is1187 pounds; the expected standard
deviation of beef sales is 1400 pounds.
Calculate the expected standard deviation of
profits, assuming pork and beef sales are
independent of one another.
o Calculate Variance
o Take Square Root of it.
Independent
Expected Standard Deviation
V(TP) = V(0.4*P + 0.5*B)
=V(0.4*P) + V(0.5*B)
Variance Calculations
The expected variance of the sum of
random variables is the sum of the
expected variances of its parts . . .
For S= aX + bY + c
V(S) = V(aX + bY + c)
=V(aX) + V(bY) + V(c)
=a2*V(X) + b2*V(Y) + 0
V(c) = 0
(. . . plus the expected covariances of its variable pairs.)
Dependent
Expected Standard Deviation
Expected Values of
Sums of 2 Random Variables
E(aX+bY)=aE(X) + bE(Y) = ax + by
V(aX+bY+cZ)=a2V(X)+b2V(Y)+c2V(Z)
+2abCOV(X,Y)+2bcCOV(Y,Z)+2caCOV(Z,X)
= a22x+b22y+c22z +2abxy+2bcyz+2cazx
A portfolio example
TVP=2I + 2M
Statistics
= . = =
..
= . . . = .
Covariance Term: . =
.
Net Exports, Xn
According to Tippler, what is expected net exports?
E(Xn)= E(X) E(M) = 75-200 = 125
What is the variance of net exports, assuming X
and M are independent?
V(Xn)= V(X M) = V(X) + V(M) = 252 + (30)2
=1525
Are X and M independent?
Tippler discovered that the correlation coefficient
between X and M is -0.50. Does this change the
variance in the previous question? If so, by how
much? If not, why not?
Questions
r = 0.50
Yes
If r = 0.50
= =
= . =
The covariance term: =
Total variance: + =
Standard Deviation of Xn= SQRT(2275) = $47.70