Date post: | 16-Apr-2017 |
Category: |
Documents |
Upload: | vu-duc-hoang-vo |
View: | 234 times |
Download: | 1 times |
1
11SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Chapter 5Chapter 5Discrete Probability DistributionsDiscrete Probability Distributions
.10.10
.20.20
.30.30
.40.40
0 1 2 3 40 1 2 3 4
■■ Random VariablesRandom Variables
■■ Discrete Probability DistributionsDiscrete Probability Distributions
■■ Expected Value and VarianceExpected Value and Variance
■■ Binomial DistributionBinomial Distribution
■■ Poisson DistributionPoisson Distribution
■■ Hypergeometric DistributionHypergeometric Distribution
22SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
A A random variablerandom variable is a numerical description of theis a numerical description of theoutcome of an experiment.outcome of an experiment.
Random VariablesRandom Variables
A A discrete random variablediscrete random variable may assume either amay assume either afinite number of values or an infinite sequence offinite number of values or an infinite sequence ofvalues.values.
A A continuous random variablecontinuous random variable may assume anymay assume anynumerical value in an interval or collection ofnumerical value in an interval or collection ofintervals.intervals.
2
33SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Let Let xx = number of TVs sold at the store in one day,= number of TVs sold at the store in one day,
where where xx can take on 5 values (0, 1, 2, 3, 4)can take on 5 values (0, 1, 2, 3, 4)
Example: JSL AppliancesExample: JSL Appliances
■■ Discrete random variable with a Discrete random variable with a finitefinite number number of valuesof values
44SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Let Let xx = number of customers arriving in one day,= number of customers arriving in one day,
where where xx can take on the values 0, 1, 2, . . .can take on the values 0, 1, 2, . . .
Example: JSL AppliancesExample: JSL Appliances
■■ Discrete random variable with an Discrete random variable with an infiniteinfinite sequence sequence of valuesof values
We can count the customers arriving, but there is noWe can count the customers arriving, but there is nofinite upper limit on the number that might arrive.finite upper limit on the number that might arrive.
3
55SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Random VariablesRandom Variables
QuestionQuestion Random Variable Random Variable xx TypeType
FamilyFamily
sizesize
xx = Number of dependents= Number of dependents
reported on tax returnreported on tax returnDiscreteDiscrete
Distance fromDistance from
home to storehome to store
xx = Distance in miles from= Distance in miles from
home to the store sitehome to the store site
ContinuousContinuous
Own dogOwn dogor cator cat
xx = 1 if own no pet;= 1 if own no pet;
= 2 if own dog(s) only; = 2 if own dog(s) only;
= 3 if own cat(s) only; = 3 if own cat(s) only;
= 4 if own dog(s) and cat(s)= 4 if own dog(s) and cat(s)
DiscreteDiscrete
66SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
The The probability distributionprobability distribution for a random variablefor a random variabledescribes how probabilities are distributed overdescribes how probabilities are distributed overthe values of the random variable.the values of the random variable.
We can describe a discrete probability distributionWe can describe a discrete probability distributionwith a table, graph, or equation.with a table, graph, or equation.
Discrete Probability DistributionsDiscrete Probability Distributions
4
77SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
The probability distribution is defined by aThe probability distribution is defined by aprobability functionprobability function, denoted by , denoted by ff((xx), which provides), which providesthe probability for each value of the random variable.the probability for each value of the random variable.
The required conditions for a discrete probabilityThe required conditions for a discrete probabilityfunction are:function are:
Discrete Probability DistributionsDiscrete Probability Distributions
ff((xx) ) >> 00
ΣΣff((xx) = 1) = 1
88SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ a tabular representation of the probabilitya tabular representation of the probabilitydistribution for TV sales was developed.distribution for TV sales was developed.
■■ Using past data on TV sales, …Using past data on TV sales, …
NumberNumber
Units SoldUnits Sold of Daysof Days
00 8080
11 5050
22 4040
33 1010
44 2020
200200
xx ff((xx))
00 .40.40
11 .25.25
22 .20.20
33 .05.05
44 .10.10
1.001.00
80/20080/200
Discrete Probability DistributionsDiscrete Probability Distributions
5
99SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
.10.10
.20.20
.30.30
.40.40
.50.50
0 1 2 3 40 1 2 3 4Values of Random Variable Values of Random Variable xx (TV sales)(TV sales)Values of Random Variable Values of Random Variable xx (TV sales)(TV sales)
Pro
bab
ilit
yP
rob
abil
ity
Pro
bab
ilit
yP
rob
abil
ity
Discrete Probability DistributionsDiscrete Probability Distributions
■■ Graphical Representation of Probability DistributionGraphical Representation of Probability Distribution
1010SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Discrete Uniform Probability DistributionDiscrete Uniform Probability Distribution
The The discrete uniform probability distributiondiscrete uniform probability distribution is theis thesimplest example of a discrete probabilitysimplest example of a discrete probabilitydistribution given by a formula.distribution given by a formula.
The The discrete uniform probability functiondiscrete uniform probability function isis
ff((xx) = 1/) = 1/nn
where:where:nn = the number of values the random= the number of values the random
variable may assumevariable may assume
the values of thethe values of therandom variablerandom variableare equally likelyare equally likely
6
1111SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Expected Value and VarianceExpected Value and Variance
The The expected valueexpected value, or mean, of a random variable, or mean, of a random variableis a measure of its central location.is a measure of its central location.
The The variancevariance summarizes the variability in thesummarizes the variability in thevalues of a random variable.values of a random variable.
The The standard deviationstandard deviation, , σσ, is defined as the positive, is defined as the positivesquare root of the variance.square root of the variance.
Var(Var(xx) = ) = σσ 22 = = ΣΣ((xx -- µµ))22ff((xx))Var(Var(xx) = ) = σσ 22 = = ΣΣ((xx -- µµ))22ff((xx))
EE((xx) = ) = µµ = = ΣΣxfxf((xx))EE((xx) = ) = µµ = = ΣΣxfxf((xx))
1212SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ Expected ValueExpected Value
expected number of expected number of TVs sold in a dayTVs sold in a day
xx ff((xx)) xfxf((xx))
00 .40.40 .00.00
11 .25.25 .25.25
22 .20.20 .40.40
33 .05.05 .15.15
44 .10.10 .40.40
EE((xx) = 1.20) = 1.20
Expected Value and VarianceExpected Value and Variance
7
1313SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ Variance and Standard DeviationVariance and Standard Deviation
00
11
22
33
44
--1.21.2
--0.20.2
0.80.8
1.81.8
2.82.8
1.441.44
0.040.04
0.640.64
3.243.24
7.847.84
.40.40
.25.25
.20.20
.05.05
.10.10
.576.576
.010.010
.128.128
.162.162
.784.784
x x -- µµ ((x x -- µµ))22 ff((xx)) ((xx -- µµ))22ff((xx))
Variance of daily sales = Variance of daily sales = σ σ 22 = 1.660= 1.660
xx
TVsTVssquaredsquared
Standard deviation of daily sales = 1.2884 TVsStandard deviation of daily sales = 1.2884 TVs
Expected Value and VarianceExpected Value and Variance
1414SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Binomial DistributionBinomial Distribution
■■ Four Properties of a Binomial ExperimentFour Properties of a Binomial Experiment
3. The probability of a success, denoted by 3. The probability of a success, denoted by pp, does, doesnot change from trial to trial.not change from trial to trial.
4. The trials are independent.4. The trials are independent.
2. Two outcomes, 2. Two outcomes, successsuccess and and failurefailure, are possible, are possibleon each trial.on each trial.
1. The experiment consists of a sequence of 1. The experiment consists of a sequence of nnidentical trials.identical trials.
stationaritystationarityassumptionassumption
8
1515SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Binomial DistributionBinomial Distribution
Our interest is in the Our interest is in the number of successesnumber of successesoccurring in the occurring in the nn trials.trials.
We let We let xx denote the number of successesdenote the number of successesoccurring in the occurring in the nn trials.trials.
1616SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
where:where:
ff((xx) = the probability of ) = the probability of xx successes in successes in nn trialstrials
nn = the number of trials= the number of trials
pp = the probability of success on any one trial= the probability of success on any one trial
( )!( ) (1 )
!( )!x n xn
f x p px n x
−= −−
Binomial DistributionBinomial Distribution
■■ Binomial Probability FunctionBinomial Probability Function
9
1717SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
( )!( ) (1 )
!( )!x n xn
f x p px n x
−= −−
Binomial DistributionBinomial Distribution
!
!( )!
n
x n x−( )(1 )x n xp p −−
■■ Binomial Probability FunctionBinomial Probability Function
Probability of a particularProbability of a particularsequence of trial outcomessequence of trial outcomeswith x successes in with x successes in nn trialstrials
Number of experimentalNumber of experimentaloutcomes providing exactlyoutcomes providing exactly
xx successes in successes in nn trialstrials
1818SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Binomial DistributionBinomial Distribution
■■ Example: Evans ElectronicsExample: Evans Electronics
Evans is concerned about a low retention rate for Evans is concerned about a low retention rate for employees. In recent years, management has seen a employees. In recent years, management has seen a turnover of 10% of the hourly employees annually. turnover of 10% of the hourly employees annually. Thus, for any hourly employee chosen at random, Thus, for any hourly employee chosen at random, management estimates a probability of 0.1 that the management estimates a probability of 0.1 that the person will not be with the company next year.person will not be with the company next year.
10
1919SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Binomial DistributionBinomial Distribution
■■ Using the Binomial Probability FunctionUsing the Binomial Probability Function
Choosing 3 hourly employees at random, what is Choosing 3 hourly employees at random, what is the probability that 1 of them will leave the company the probability that 1 of them will leave the company this year?this year?
f xn
x n xp px n x( )
!!( )!
( ) ( )=−
− −1
1 23!(1) (0.1) (0.9) 3(.1)(.81) .243
1!(3 1)!f = = =
−
LetLet: p: p = .10, = .10, nn = 3, = 3, xx = 1= 1
2020SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ Tree DiagramTree Diagram
Binomial DistributionBinomial Distribution
1st Worker1st Worker 2nd Worker2nd Worker 3rd Worker3rd Worker xx Prob.Prob.
Leaves(.1)
Leaves(.1)
Stays(.9)
Stays(.9)
33
22
00
22
22
Leaves (.1)Leaves (.1)
Leaves (.1)Leaves (.1)
S (.9)S (.9)
Stays (.9)Stays (.9)
Stays (.9)Stays (.9)
S (.9)S (.9)
S (.9)S (.9)
S (.9)S (.9)
L (.1)L (.1)
L (.1)L (.1)
L (.1)L (.1)
L (.1)L (.1) .0010.0010
.0090.0090
.0090.0090
.7290.7290
.0090.0090
11
11
.0810.0810
.0810.0810
.0810.0810
1111
11
2121SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ Using Tables of Binomial ProbabilitiesUsing Tables of Binomial Probabilities
n x .05 .10 .15 .20 .25 .30 .35 .40 .45 .50
3 0 .8574 .7290 .6141 .5120 .4219 .3430 .2746 .2160 .1664 .1250
1 .1354 .2430 .3251 .3840 .4219 .4410 .4436 .4320 .4084 .3750
2 .0071 .0270 .0574 .0960 .1406 .1890 .2389 .2880 .3341 .3750
3 .0001 .0010 .0034 .0080 .0156 .0270 .0429 .0640 .0911 .1250
p
Binomial DistributionBinomial Distribution
2222SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Binomial DistributionBinomial Distribution
(1 )np pσ = −
EE((xx) = ) = µµ = = npnp
Var(Var(xx) = ) = σσ 22 = = npnp(1 (1 −− pp))
■■ Expected ValueExpected Value
■■ VarianceVariance
■■ Standard DeviationStandard Deviation
12
2323SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Binomial DistributionBinomial Distribution
3(.1)(.9) .52 employeesσ = =
EE((xx) = ) = µµ = 3(.1) = .3 employees out of 3= 3(.1) = .3 employees out of 3
Var(Var(xx) = ) = σσ 22 = 3(.1)(.9) = .27= 3(.1)(.9) = .27
■■ Expected ValueExpected Value
■■ VarianceVariance
■■ Standard DeviationStandard Deviation
2424SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
A Poisson distributed random variable is oftenA Poisson distributed random variable is oftenuseful in estimating the number of occurrencesuseful in estimating the number of occurrencesover a over a specified interval of time or spacespecified interval of time or space
It is a discrete random variable that may assumeIt is a discrete random variable that may assumean an infinite sequence of valuesinfinite sequence of values (x = 0, 1, 2, . . . ).(x = 0, 1, 2, . . . ).
Poisson DistributionPoisson Distribution
13
2525SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Examples of a Poisson distributed random variable:Examples of a Poisson distributed random variable:
the number of knotholes in 14 linear feet ofthe number of knotholes in 14 linear feet ofpine boardpine board
the number of vehicles arriving at athe number of vehicles arriving at atoll booth in one hourtoll booth in one hour
Poisson DistributionPoisson Distribution
2626SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Poisson DistributionPoisson Distribution
■■ Two Properties of a Poisson ExperimentTwo Properties of a Poisson Experiment
2.2. The occurrence or nonoccurrence in anyThe occurrence or nonoccurrence in anyinterval is independent of the occurrence orinterval is independent of the occurrence ornonoccurrence in any other interval.nonoccurrence in any other interval.
1.1. The probability of an occurrence is the sameThe probability of an occurrence is the samefor any two intervals of equal length.for any two intervals of equal length.
14
2727SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ Poisson Probability FunctionPoisson Probability Function
Poisson DistributionPoisson Distribution
f xe
x
x( )
!=
−µ µ
where:where:
f(x) f(x) = probability of = probability of xx occurrences in an intervaloccurrences in an interval
µµ = mean number of occurrences in an interval= mean number of occurrences in an interval
ee = 2.71828= 2.71828
2828SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Poisson DistributionPoisson Distribution
MERCYMERCY
■■ Example: Mercy HospitalExample: Mercy Hospital
Patients arrive at the Patients arrive at the
emergency room of Mercyemergency room of Mercy
Hospital at the averageHospital at the average
rate of 6 per hour onrate of 6 per hour on
weekend evenings. weekend evenings.
What is theWhat is the
probability of 4 arrivals inprobability of 4 arrivals in
30 minutes on a weekend evening?30 minutes on a weekend evening?
15
2929SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Poisson DistributionPoisson Distribution
■■ Using the Poisson Probability FunctionUsing the Poisson Probability Function
4 33 (2.71828)(4) .1680
4!f
−
= =
MERCYMERCY
µµ = 6/hour = 3/half= 6/hour = 3/half--hour, hour, xx = 4= 4
3030SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Poisson DistributionPoisson Distribution
■■ Using Poisson Probability TablesUsing Poisson Probability Tables
µµµµx 2.1 2.2 2.3 2.4 2.5 2.6 2.7 2.8 2.9 3.0
0 .1225 .1108 .1003 .0907 .0821 .0743 .0672 .0608 .0550 .0498
1 .2572 .2438 .2306 .2177 .2052 .1931 .1815 .1703 .1596 .1494
2 .2700 .2681 .2652 .2613 .2565 .2510 .2450 .2384 .2314 .2240
3 .1890 .1966 .2033 .2090 .2138 .2176 .2205 .2225 .2237 .2240
4 .0992 .1082 .1169 .1254 .1336 .1414 .1488 .1557 .1622 .1680
5 .0417 .0476 .0538 .0602 ..0668 .0735 .0804 .0872 .0940 .1008
6 .0146 .0174 .0206 .0241 .0278 .0319 .0362 .0407 .0455 .0504
7 .0044 .0055 .0068 .0083 .0099 .0118 .0139 .0163 .0188 .0216
8 .0011 .0015 .0019 .0025 .0031 .0038 .0047 .0057 .0068 .0081
MERCYMERCY
16
3131SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ Poisson Distribution of ArrivalsPoisson Distribution of Arrivals
Poisson DistributionPoisson DistributionMERCYMERCY
Poisson Probabilities
0.00
0.05
0.10
0.15
0.20
0.25
0 1 2 3 4 5 6 7 8 9 10Number of Arrivals in 30 Minutes
Pro
ba
bil
ity
actually, actually, the sequencethe sequence
continues:continues:11, 12, …11, 12, …
3232SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Poisson DistributionPoisson Distribution
A property of the Poisson distribution is thatA property of the Poisson distribution is thatthe mean and variance are equal.the mean and variance are equal.
µµ = = σ σ 22
17
3333SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Poisson DistributionPoisson DistributionMERCYMERCY
■■ Variance for Number of ArrivalsVariance for Number of Arrivals
During 30During 30--Minute PeriodsMinute Periods
µµ = = σσ 22 = 3 = 3
3434SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Hypergeometric DistributionHypergeometric Distribution
The The hypergeometric distributionhypergeometric distribution is closely relatedis closely relatedto the binomial distribution. to the binomial distribution.
However, for the hypergeometric distribution:However, for the hypergeometric distribution:
the trials are not independent, andthe trials are not independent, and
the probability of success changes from trialthe probability of success changes from trialto trial. to trial.
18
3535SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ Hypergeometric Probability FunctionHypergeometric Probability Function
Hypergeometric DistributionHypergeometric Distribution
−−
=
n
N
xn
rN
x
r
xf )( for 0 for 0 << xx << rr
where: where: ff((xx) = probability of ) = probability of xx successes in successes in nn trialstrials
nn = number of trials= number of trials
NN = number of elements in the population= number of elements in the population
rr = number of elements in the population= number of elements in the population
labeled successlabeled success
3636SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
■■ Hypergeometric Probability FunctionHypergeometric Probability Function
Hypergeometric DistributionHypergeometric Distribution
( )
r N r
x n xf x
N
n
− −
=
for 0 for 0 << xx << rr
number of waysnumber of waysnn –– x x failures can be selectedfailures can be selectedfrom a total of from a total of NN –– rr failuresfailures
in the populationin the population
number of waysnumber of waysxx successes can be selectedsuccesses can be selectedfrom a total of from a total of rr successessuccesses
in the populationin the populationnumber of waysnumber of ways
a sample of size a sample of size n n can be selectedcan be selectedfrom a population of size from a population of size NN
19
3737SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Hypergeometric DistributionHypergeometric Distribution
■■ Example: NevereadyExample: Neveready
Bob Neveready has removed twoBob Neveready has removed two
dead batteries from a flashlight anddead batteries from a flashlight and
inadvertently mingled them withinadvertently mingled them with
the two good batteries he intendedthe two good batteries he intended
as replacements. as replacements. The four batteries look identical.The four batteries look identical.
Bob now randomly selects two of the four Bob now randomly selects two of the four batteries. What is the probability he selects the two batteries. What is the probability he selects the two good batteries?good batteries?
3838SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Hypergeometric DistributionHypergeometric Distribution
■■ Using the Hypergeometric FunctionUsing the Hypergeometric Function
2 2 2! 2!
2 0 2!0! 0!2! 1( ) .167
4 4! 6
2 2!2!
r N r
x n xf x
N
n
− − = = = = =
where:where:xx = 2 = number of = 2 = number of goodgood batteries selectedbatteries selectednn = 2 = number of batteries selected= 2 = number of batteries selectedNN = 4 = number of batteries in total= 4 = number of batteries in totalrr = 2 = number of = 2 = number of goodgood batteries in totalbatteries in total
20
3939SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Hypergeometric DistributionHypergeometric Distribution
( )r
E x nN
µ = =
2( ) 11
r r N nVar x n
N N Nσ − = = − −
■■ MeanMean
■■ VarianceVariance
4040SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Hypergeometric DistributionHypergeometric Distribution
22 1
4
rn
Nµ = = =
2 2 2 4 2 12 1 .333
4 4 4 1 3σ − = − = = −
■■ MeanMean
■■ VarianceVariance
21
4141SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Hypergeometric DistributionHypergeometric Distribution
Consider a hypergeometric distribution with Consider a hypergeometric distribution with nn trialstrialsand let and let pp = (= (rr//nn) denote the probability of a success) denote the probability of a successon the first trial.on the first trial.
If the population size is large, the term (If the population size is large, the term (NN –– nn)/()/(NN –– 1)1)
approaches 1.approaches 1.
The expected value and variance can be writtenhe expected value and variance can be written
EE((xx) = ) = npnp and and VarVar((xx) = ) = npnp(1 (1 –– pp).).
Note that these are the expressions for the expectedhe expected
value and variance of a binomial distribution.value and variance of a binomial distribution.
continuedcontinued
4242SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
Hypergeometric DistributionHypergeometric Distribution
When the population size is large, a hypergeometricWhen the population size is large, a hypergeometricdistribution can be approximated by a binomialdistribution can be approximated by a binomialdistribution with distribution with nn trials and a probability of successtrials and a probability of successpp = (= (rr//NN). ).
22
4343SlideSlide© 2005 Thomson/South© 2005 Thomson/South--WesternWestern
End of Chapter 5End of Chapter 5