Sc0x w4l2 Clean

Managing
Uncertainty II
Continuous Distributions
MIT Center for

Transportation & Logistics
ctl.mit.edu
Zippy Bright DCs

Zippy Bright manufactures electric toothbrushes that are sold through large
retail outlets. Currently, they distribute one of their premiere products, the
XP219, from three Distribution Centers (East, Center, and West) to more than
3500 stores. The weekly demand that the East DC faces is shown in the data
table below.
What can we say about the weekly demand for this DC?
Week Unit Sales
1 3595
2 3011
3 2994
4 3576
5 3697
6 2648
7 3747
8 3165
9 3412
10 2750
MIT Center for

Week Unit Sales

11 2346
12 2869
13 3450
14 2031
15 3198
16 2939
17 2034
18 2476
19 2339
20 3200
Week Unit Sales

21 3967
22 2844
23 2546
24 2771
25 4084
26 2755
27 2641
28 2875
29 3855
30 2880
Week Unit Sales

31 2898
32 3713
33 2845
34 2866
35 3549
36 2365
37 2462
38 2480
39 3055
40 2453
Week Unit Sales

41 2196
42 3469
43 3570
44 2071
45 3247
46 4740
47 2316
48 2625
49 3973
50 3491
Summary Statistics for Spreadsheets

Function
Microsoft Excel
Google Sheets
LibreOffice->Calc
Minimum
=MIN(array)
=MINA(array)
=MIN(array)
Median
=MEDIAN(array)
=MEDIAN(array)
=MEDIAN(array)
Mode
=MODE(array)
=MODE(array)
=MODE(array)
Mean ()
=AVERAGE(array)
=AVERAGE(array)
=AVERAGE(array)
Maximum
=MAX(array)
=MAX(array)
=MAX(array)
Percentile
=PERCENTILE.INC(array, k)
=PERCENTILE(array,
percentile)
=PERCENTILE.INC(array,
alpha)
=VAR.P(array)
=VARP(array)
=VAR.P(array)
Sample Variance (2)
=VAR.S(array)
=VAR(array)
=VAR.S(array)
Pop. Std Deviation ()
=STDEV.P(array)
=STDEVP(array)
=STDEV.P(array)
Sample Std Deviation ()
=STDEV(array)
=STDEV(array)
=STDEV.S(array)
Population Variance (2)
A Note on Population versus Sample Variance . . .
In real-life, we usually do not know the true mean of the

population. Instead, we need to estimate it from a sample.
An unbiased estimate of the variance is shown, s2
MIT Center
forthe sample variance and standard deviation
In practice,
use
(x )
2
pop
i=1
2
sample
(x x )
=
i=1
n 1
Zippy Bright DC-East: Weekly Demand
Minimum
Median
Mean ()
Maximum
2,031
2,889
3,022
4,740
MIT Center for

Range 2,709
Inner-Quartile Range
920
Variance (2) 356,269
Std Deviation ()
603
Coefficient of Variation
0.20
25th Percentile
50th Percentile (Median)
75th Percentile
2,566
2,889
3,486
4
MIT Center for

Why not just Discretize the Data?
Which histogram should we use?

60%
40%
50%
60%
50%
40%
30%
20%
10%
0%
30%
40%
20%
30%
20%
10%
10%
0%
0%
3000
3500
4000
4500
MIT Center for

5000
2500 3000 3500 4000 4500 5000
2500
3500
5000
12%
5000
4900
4800
4700
4600
4500
4400
4300
4200
4100
4000
3900
3800
3700
3600
3500
3400
3300
3200
3100
3000
2900
2800
2700
2600
2500
2400
2300
2200
2100
2000
1900
1800
1700
1600
1
0
1500
Weekly Demand at Eastern DC
Weekly demand at Eastern DC

in 100 unit bins for the last year.
10%
8%
6%
4%
2%
0%
MIT Center for

Continuous Probability Distributions

Differences from Discrete Random Variables
n
n
n
Probability of specific value outcomes make no sense

Probability of values within an interval is more helpful
Cannot list all possible outcomes instead we need to use a function
Probability Density Function (pdf)

n
probability
Probability that X lies between values a and b is equal to area under

the curve between a and b
Total area under the curve equals 1, but the P[X=t] = 0!
a
MIT Center for
b
a
f (t)dt
t
8
Continuous vs. Discrete Distributions

Discrete
Continuous
Multiply each value by

its probability
Requires integration to
calculate and 2
= E( X ) = pi xi
= t f (t )dt
i=1
2 = pi (xi ) 2
= (t ) 2 f (t )dt
a
probability
probability
i=1
pmf
MIT Center for

pdf
f(t)
Continuous Probability Distributions

Cumulative Density Function (cdf)
n
n
n
F(t) = P(Xt) or the probability that X does not exceed t

0.0 F(t) 1.0
F(b) F(a) if b>a it is increasing
Simple Rules
n
n
n
P(Xt) = F(t)
P(X>t) = 1 F(t)
P(cXd) = F(d) F(c)
P(X=t) = 0
F(t)
F(a)
0
probability
cdf
cumulative probability
1.0
MIT Center for

t
pdf
f(t)
t
10
MIT Center for

Source: Wikipedia
11
Uniform Distribution
MIT Center for

12
Uniform Distribution
We would say,
X is uniformly distributed over
the range a to b, or X~U(a,b)
1
if a t b
f (t | a, b) = b a
0
otherwise
0 if t < a
!
"
"t a
=
F (t | a, b) %
if a t b
"b a
"&
1 if t > b
1
Mean = a + b
2
1
Median = a + b
2
Mode = any value in range [a,b]
1
2
Variance = b a
12
MIT Center for

13
Zippy Bright Transportation I

Zippy Bright has a consumer delivery unit. They distribute
product from a downtown location to all residences and offices in
the city. The deliveries are made on scooters and each customer
is delivered to directly. They found that the distance to each
customer location is ~U(2.75,6.50) kilometers.
1. What is the average distance, median distance, and CV?
We know that mean = (a+b)/2 = (2.75 + 6.50)/2 = 4.625 km which is also the median!
CV= /= [(1/12)(b-a)2] / (a+b)/2 = [(1/12)(6.5 2.75)2] / 4.625 = 1.0825 / 4.625 = 0.23
2. What is the probability that distance >5 km?

F(t) = P[Xt], since we want to find P[X>t], we need to find 1-F(t) = 1 (t-a)/(b-a)
= 1 (5-2.75) / (6.5 2.75) = 1 0.6 = 0.40 or 40%.
3. What is the probability that distance is +/- 1 of the ?

We know that = 1.0825 and that =4.625. So, we want to find, the probability that X is
between (4.625 1.0825) and (4.625 + 1.0825) or [3.5425, 5.7075].
We can find this using the cdf: F(5.7075) F(3.5425) = 0.789 0.211 = 0.577 = 58%
MIT Center for
14
Normal Distribution
MIT Center for

15
Normal Distribution
We would say,
X is normally distributed with mean
and standard deviation , or X~N(, )
Note: mean=median=mode =
1
f ( x | , ) =
e
1/ 2
(2 )
1 x 2

2
fx(x0)
Area =
P[x<+kx]
Area =
P[x+kx]
=1-P[x<+kx]
+kx
x0
Characteristics
Most commonly used distribution many analyses assume ~ N

High point in bell curve occurs at mean
Symmetric about the mean
The mean shifts the distribution but not the shape
The standard deviation changes the shape but doesnt shift it
MIT Center for

16
The Normal Distribution
+/- 2
+/-
60
0
65
0
70
0
65
0
70
0
55
0
55
0
60
0
50
0
45
0
40
0
35
0
30
0
20
0
+/- 1.65 around = 0.900

+/- 1.96 around = 0.950
+/- 2.81 around = 0.995
0.6%
0.5%
0.4%
0.3%
0.2%
0.1%
0.0%
25
0
Common dispersion metrics ~N(,)

P(X w/in 1 around ) = .6826
Probability of X
Normal Distribution
Value
Normal CDF
So, what is 6?
_10
Error occurs 9.9 x 10
of the time
Probability of X
100%
80%
60%
40%
20%
45
0
50
0
40
0
30
0
35
0
25
0
20
0
0%
Value
MIT Center for

17
Unit or Standard Normal Distribution

Standard Normal Distribution (z scores)
n
n
n
n
n
n
n
Z~N(0,1) where Z=(X-)/

Z score gives the number of standard deviations away from the mean
Allows for use of standard tables
Used extensively in inventory theory for setting safety stock
Area under the curve is 1
Able to assess the probability of an event
A z score can be positive or negative
fu(u0)
( )
f u u0 =
Area =
P[u<z]
Area =
P[uz]=
=1-P[u<z]
0
MIT Center for
x02
2
u0
18
Normal Functions for Spreadsheets

Function
cdf of Normal
Distribution
pdf of Normal
Distribution
Inverse of Normal
cdf
Standard Normal cdf
Inverse Standard
Normal cdf
Microsoft Excel
Google Sheets
LibreOffice->Calc
=NORM.DIST(X, , , 1)
=NORMDIST (X, , , 1)
=NORM.DIST (X, , , 1)
=NORM.DIST(X, , , 0)
=NORMDIST (X, , , 0)
=NORM.DIST (X, , , , 0)
=NORM.INV(Probability, , )
=NORMINV (Probability, , )
=NORM.INV (Probability, , )
=NORM.S.DIST(z,1)
=NORM.S.INV(Probability)
=NORMSDIST (z)
=NORMSINV (Probability)
=NORM.S.DIST (z,1)
=NORM.S.INV (Probability)
Examples for ~N(100, 12):

What is P[X<85]?
=NORM.DIST(85, 100, 12, 1) = 0.105 = 10.5%
What value of X covers 75% of the probability?
= NORM.INV (0.75, 100, 12) = 108.09 = 108
How many standard deviations does it take to cover 99.99%?
= NORM.S.INV(.9999) = 3.719
What probability is covered by 1.65 standard deviations over the mean?
= NORM.S.DIST(1.65,1) = 0.95 = 95%
MIT Center for
19
Zippy Bright Transportation II

is delivered to directly. They found that the distance to each
customer location is ~N(4.6, 1.10) kilometers.
1. What is the average distance, median distance, and CV?
This is trivial since they are all given! Average = median = 4.6 km. CV=/=1.1/4.6 = 0.24

We want to find P[X>5] = 1- P[X5] = 1 - NORM.DIST(5, 4.6, 1.1, 1) = 1- 0.643 = 0.36 or 36%
3. What is the probability that distance is +/- 1 around the mean?

By definition, 68.3%. But we could also use the cdf functions.
P[X5.7] P[X3.5] = NORM.DIST(5.7, 4.6, 1.1, 1) NORM.DIST(3.5, 4.6, 1.1, 1)
= 0.841 - 0.158 = 0.683 or 68.3%
MIT Center for

20
Triangle Distribution
MIT Center for

21
Triangle Distribution
2
(b a)
We would say,
X follows a triangle distribution
with a minimum of a, maximum
b, and a mode of c, ~T(a, b, c)
#
0
%
%
2 xa
%
% ba ca
f (x) = $
2 b x
%
%
% ba bc
%
0
&
)(
x<a
)(
axc
c xb
x>b
b x
a+b+c
E x =
3
1 2 2 2
Var x = a + b + c ab ac bc
18
2
P x > d =
for c d b
ba bc
)(
)(
d = b P x > d b a b c
for c d b
Characteristics
MIT Center for

Good way to get a sense of an unknown distribution

People tend to recall extreme and common values
Handles asymmetric distributions
22
Zippy Bright Transportation III

is delivered to directly. No one recalls exactly what the distance
to each customer location is, but the consensus is that the
shortest is about 1 km, the longest is about 7 km, and the most
common is probably 4 km.
1. What is the average distance and CV?
1 2 2 2
Var x = a + b + c ab ac bc
18
Average = (a+b+c)/3 = (1 + 7 + 4)/3 = 4 km
Plugging in, 2= 1.50 so = 1.225 and CV = 1.225/4 = 0.31

We want P[X>5] and since 457, we can plug in and find P[x>5] = 22%
2
P x > d =
ba bc
MIT Center for

)(
for c d b
23
Key Points from Lesson
MIT Center for

24
Key Points from Lesson
MIT Center for

25
Questions, Comments, Suggestions?

Use the Discussion Forum!
Uniformly fun!
MIT Center for

MIT Center for

[email protected]
ctl.mit.edu

Sc0x w4l2 Clean

Uploaded by

Copyright:

Available Formats

Sc0x w4l2 Clean

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Sc0x w4l2 Clean

Uploaded by

Copyright:

Available Formats

Managing

MIT Center for

Zippy Bright DCs

MIT Center for

Week Unit Sales

Week Unit Sales

Week Unit Sales

Week Unit Sales

Summary Statistics for Spreadsheets

Sample Variance (2)

Pop. Std Deviation ()

Sample Std Deviation ()

Population Variance (2)

A Note on Population versus Sample Variance . . .

In real-life, we usually do not know the true mean of the

Zippy Bright DC-East: Weekly Demand

MIT Center for

MIT Center for

Why not just Discretize the Data?

Which histogram should we use?

MIT Center for

2500 3000 3500 4000 4500 5000

Weekly Demand at Eastern DC

Weekly demand at Eastern DC

MIT Center for

Continuous Probability Distributions

Probability of specific value outcomes make no sense

Probability Density Function (pdf)

Probability that X lies between values a and b is equal to area under

Continuous vs. Discrete Distributions

Multiply each value by

MIT Center for

Continuous Probability Distributions

F(t) = P(Xt) or the probability that X does not exceed t

MIT Center for

MIT Center for

MIT Center for

MIT Center for

Zippy Bright Transportation I

2. What is the probability that distance >5 km?

3. What is the probability that distance is +/- 1 of the ?

MIT Center for

Most commonly used distribution many analyses assume ~ N

MIT Center for

The Normal Distribution

+/- 1.65 around = 0.900

Common dispersion metrics ~N(,)

Error occurs 9.9 x 10

MIT Center for

Unit or Standard Normal Distribution

Z~N(0,1) where Z=(X-)/

Normal Functions for Spreadsheets

Examples for ~N(100, 12):

Zippy Bright Transportation II

2. What is the probability that distance >5 km?

3. What is the probability that distance is +/- 1 around the mean?

MIT Center for

MIT Center for

MIT Center for