Upload
others
View
13
Download
0
Embed Size (px)
Citation preview
1
Essential Mathematics (For business and economic analysis)
Course: Business Mathematics II. Mat 211 Dr. Firoz
Chapter 8 Discrete and Continuous Distribution
Section 8.1 Random variables of the discrete type
In probability theory, a probability distribution is called discrete if it is characterized by a
probability mass function. Thus, the distribution of a random variable X is discrete, and X
is then called a discrete random variable, if ( ) 1p X
If a random variable is discrete, then the set of all values that it can assume with non-zero
probability is finite or countably infinite, because the sum of uncountably many positive
real numbers (which is the least upper bound of the set of all finite partial sums) always
diverges to infinity.
Given a random experiment with an outcome space S, a function X that assigns to each
element s in S one and only one real number X(s) = x is called a random variable, like a
function of s. The space of X is the set of real numbers { : ( ) , }x X s x s S , where s S
means the element s belongs to S. The probability mass function (pmf) ( )f x of a
discrete random variable X is a function that satisfies the following properties:
1. ( ) 0, ;f x x S
2. ( ) 1;x S
f x
3. ( ) ( ),x A
P X A f x A S
Example 1. Suppose that X has a discrete uniform distribution on {1,2,3,4,5,6}S and
its pmf is 1
( ) , 1,2,3,4,5,66
f x x .
As a general case we may write pmf as 1
( ) , 1,2,3,4, ,f x x mm
Example 2. Roll a 4 –sided die twice and let X equal the larger of the two outcomes if
they are different and common value if they are the same. The outcome space for this
experiment is 0 1 2 1 2{( , ); 1,2,3,4; 1,2,3,4}S d d d d , where we assume that each of
these 16 points has probability 1
16. Then
1 3 5( 1) [(1,1)] , ( 2) [{(1,2),(2,2), (2,1)] , ( 3)]
16 16 16P X P P X P P X and
7( 4)
16P X . Looking at the pattern one can easily find the pmf
2
2 1( ) , 1,2,3,4
16
xf x x
Exercise
1. Let the pmf of X be defined by ( ) , 2,3,49
xf x x , a) draw a bar graph and a
b) probability histogram
2. For each of the following, determine the constant c, so that ( )f x satisfies the
conditions of being a pmf for a random variable X,
a) ( ) , 1,2,3,4x
f x xc
b) ( ) , 1,2,3,4 10f x cx x
c) 1
( ) , 1,2,3,44
x
f x c x
d) 2( ) (1 ) , 0,1,2,3f x c x x
e) ( ) , 1,2,3,4, ,x
f x x nc
Section 8.3 Mathematical expectation
In probability theory and statistics, the expected value (or expectation value, or
mathematical expectation, or mean, or first moment) of a random variable is the
integral of the random variable with respect to its probability measure.
For discrete random variables this is equivalent to the probability-weighted sum of the
possible values.
The term "expected value" can be misleading. It must not be confused with the "most
probable value." The expected value is in general not a typical value that the random
variable can take on. It is often helpful to interpret the expected value of a random
variable as the long-run average value of the variable over many independent repetitions
of an experiment.
When it exists, mathematical expectation E satisfies the following properties:
a) If c is a constant, ( )E c c
b) If c is a constant and u is a function, [ ( )] [ ( )]E cu x cE u x
c) If 1c and 2c are constants and 1u and 2u are functions, than
1 1 2 2 1 1 2 2[ ( ) ( )] [ ( )] [ ( )]E c u X c u X c E u X c E u X
3
Example 1. Let X have the pmf ( ) , 1,2,3,410
xf x x . Find ( )E X
Solution: 1
( ) ( ) 310
x
i i
x
xE X x f x x , verify.
Example 2. Let X have the pmf ( ) , 1,2,36
xf x x . Find mean = ( )E X and also
2( )E X and variance 2 2 2( ) ( ( ))E X E X and also standard deviation .
Solution: Mean = 1
7( ) ( )
6 3
x
i i
x
xE X x f x x
2 2 2
1
36( ) ( ) 6
6 6
x
i i
x
xE X x f x x
Variance
2
2 2 2 7 5( ) ( ( )) 6
3 9E X E X and
5
3
Example 3. A politician can emphasize jobs or the environment in her election
campaign. The voters can be concerned about jobs or the environment. A payoff matrix
showing the utility of each possible outcome is shown.
Jobs Voters Environment
Jobs 25 10
Environment 15 30
The political analysts feel there is a 0.39 chance that the voters will emphasize
jobs. Which strategy should the candidate adopt to gain the highest utility
a) Environment b) Jobs
Explain mathematically.
Solution: For the environment the expected value is ( ) 15(.39) 30(1 .39) 12.45E x
On the other hand for jobs the expected value is ( ) 25(.39) 10(1 .39) 3.65E x . So
the preference will go for a) Environment (because of higher expected value).
Exercise
1. Find mean and standard deviation of the following:
a) 1
( ) , 5,10,15,20,255
f x x
b) ( ) 1, 5f x x
c) 4
( ) , 1,2,36
xf x x
2. Given 2( 4) 10, [( 4) ] 116E X E X , determine 2 Var ( 4)X and
mean= ( )E X
4
Section 8.2 Bernoulli trials and the Binomial distribution
A Bernoulli experiment is a random experiment, the outcome of which can be classified
in but one of two mutually exclusive and exhaustive ways, say, success or failure (life or
death, head or tail, 3 or not 3 etc. The pmf of a Bernoulli trail is 1( ) (1 ) , 0,1x xf x p p x and we say that the random variable x has Bernoulli
distribution. The mean of Bernoulli trial is given as 1
1
0
( ) (1 )x x
x
E X xp p p , verify.
The variance of Bernoulli trial is 1
2 2 1
0
( ) ( ) (1 ) (1 ) , 1x x
x
Var X x p p p p p pq q p
Example 1. In the instant lottery with 20% winning tickets, if X is equal to the number of
winning tickets among n = 8 that are purchased, the probability of purchasing two
winning tickets is 2 68
(2) ( 2) (0.20) (1 0.2) 0.2936 29.36%2
f P X
One may use calculator as follows (TI)
2nd
DISTR 0 (binompdf) (8, 0.20, 2) will display 0.29360128
Example 2. In the instant lottery with 20% winning tickets, if X is equal to the number of
winning tickets among n = 8 that are purchased, the probability of purchasing at best 6
winning tickets is
7 1 88 8
( 6) 1 (7) (8) 1 (0.20) (1 0.2) (0.2) 0.999915527 8
P X f f
One may use calculator as follows (TI)
2nd
DISTR A (binomcdf) (8, 0.20, 6) will display 0.99991552
Example 3. In the instant lottery with 20% winning tickets, if X is equal to the number of
winning tickets among n = 8 that are purchased. Find the probability of purchasing at
least 6 winning tickets.
Hint. Find ( 6) ( 6) ( 7) ( 8)P X P X P X P X or
( 6) 1 ( 5) 1 (8,.2,5)P X P X binomcdf
Example 4. A quiz consists of 24 multiple choice questions. Each question has 5 possible
answers, only one of which is correct. If you answer the questions completely based on
guessing, what is the probability that
a) You will answer exactly 4 wrong?
b) You will answer exactly 4 correctly?
c) You will answer at least 20 correctly?
d) You will answer at most 3 wrong?
e) You will answer at most 3 correctly?
5
Solution: The probability that you will answer one question wrong is 4
0.85
.
a) The probability of answering exactly 4 wrong is a binomial probability of
B(24, 0.8, 4), which is 4 20 1124
( 4) (24,0.8,4) (0.8) (0.2) 4.56 104
P X B ,
which is almost zero.
If you use TI calculator use binompdf (24, 0.8, 4). Check your calculator using the
following code:
2nd
DISTR 0 binompdf (24, .8, 4)
b) The probability that you will answer exactly 4 correct is B(24, 0.2, 4) = 0.196
c) At least 20 correct ( 20)P X
= 20 correct + 21 correct + 22 correct + 23 correct + 24 correct = 114.79 10 .
It is easy to use calculator with binomcdf as follows: 11( 20) 1 (24,0.2,19) 4.79 10P X binomcdf
d) At most three wrong: 12( 3) (24,0.8,3) 2.25 10P X binomcdf
e) At most three correct: ( 3) (24,0.2,3) 0.264P X binomcdf
Example 5. A computer manufacturer tests a random sample of 28 computers. The
probability that a computer is non defective is 91.3%. What is the probability that:
a) Exactly 7 computers are defective? Answer: 0.006605
b) At least two computers are defective? Answer: 0.7131689
c) At most two computers are defective? Answer: 0.555224
Example 6. A quiz consists of 10 multiple choice questions, each with 4 possible
choices. For someone who makes random guesses for all of the questions, find the
probability of passing if the minimum passing grade is 90%.
Solution: 5( 9) 1 (10,0.25,8) 2.95639 10P X binomcdf
Example 8. A student claims that he has extrasensory perception (ESP). A coin is flipped
25 times, and a student is asked to predict the outcome in advance. He gets 20 out of 25
correct. What was the probability that he would have done at least this well if he had no
EPS?
Solution: ( 20) 1 (25,0.5,19) 0.002038658P X binomcdf
Exercise 1. Toss a fair coin 12 times. How many possible outcomes do you have? What
is the probability of getting a) exactly 7 heads, b) at least 7 heads, c) at most 7 heads?
6
Exercise 2. A student claims that he has extrasensory perception (ESP). A coin is flipped
30 times, and a student is asked to predict the outcome in advance. He gets 25 out of 30
correct. What was the probability that he would have done at least this well if he had no
EPS?
Exercise 3. A quiz consists of 20 multiple choice questions, each with 5 possible choices.
For someone who makes random guesses for all of the questions, find the probability of
passing if the minimum passing grade is 80%.
Example 4. A computer manufacturer tests a random sample of 30 computers. The
probability that a computer is defective is 7
78
%. What is the probability that:
a) Exactly 7 computers are defective?
b) At least two computers are defective?
c) At most two computers are defective?
Exercise 5. In the instant lottery with 10% winning tickets, if X is equal to the number of
winning tickets among 20 tickets that are purchased, find the probability of purchasing
a) at best 7 winning tickets,
b) at least 7 winning tickets,
c) no more than 6 winning tickets,
d) no less than 6 winning tickets
Exercise 6. The rates of on-time flights for commercial jets are continuously tracked by
the U.S Department of transportation. Recently, Southwest Air had the best rate with
80% of its flights arriving on time. A test is conducted by randomly selected 16
Southwest flights and observing whether they arrive on time. Find
a) the probability that exactly 4 flights arrive on time
b) The probability that at least 4 flights arrive on time
c) At best 4 flights arrive on time
Appendix P.1 Random variable of the continuous type
A random variable is a function X that assigns to each element s in the outcome space S
one and only one corresponding real number X(s) = x. The space of X is the set of real
numbers { : ( ) , }S x X s x s S is an interval. In discrete case the S is the set of discrete
points. In the continuous case we call the integrable function ( )f x , a probability
density function (pdf) which satisfies the following:
a) ( ) 0,f x x S b) ( ) 1S
f x dx
c) The probability of the event X A is ( ) ( )A
P X A f x dx
Probability Distribution Function: A function F is a distribution function of the
random variable X iff the following conditions are satisfied:
a) F is non decreasing i.e., 0F , or ( ) ( )F x F y for all x y
b) F is continuous c) F is normalized i.e., lim ( ) 0; lim ( ) 1x x
F x F x
7
Example 1. Evaluate the integral / 20
020
xedx
Solution: / 20
/ 20
00
lim 120
xb
x
b
edx e
Example 2. Show that ( ) , 0mxe
f x xm
is a probability density function.
Solution (Hint): Show that ( ) 0f x and /
0
1x me
dxm
Example 3. Let Y be a continuous random variable with pdf ( ) 2 , 0 1g y y y and the
distribution function is defined by
2
0
0 0
( ) 2 0 1
1 1
y
y
G y t dt y y
y
Find mean
1
0
2( ) ( )
3E Y yg y dy (check the integral) and
Variance
1
2 2 2 2 2
0
1( ) ( ) ( )
18Var Y E Y y g y dy (check the integral). Find
also the standard deviation .
Example 4. The probability density function of a continuous random variable x is given
as ( ) 1 1 , 0 2f x x x . Find its corresponding distribution function, mean,
variance and standard deviation, interval of one standard deviation of mean, two standard
deviation of mean and three standard deviation of mean.
Solution: The distribution function is the integral of the 1
pdf function over the real line.
Draw the graph of the pdf and notice that F(0) = 0,
0 1 2
F(1) = 1/2 and F(2) = 1. We also notice that distribution function is zero, i.e., (0) 0F
when x < 0.
The distribution function over the interval 0 1x is 2
( ) (1 1) (1 (1 ) , 0,as (0) 02
xF x x dx x dx x dx c c F
The distribution function over the interval 1 2x is 2 1
( ) (1 1) (1 1) (2 ) 2 , 1, (1)2 2
xF x x dx x dx x dx x c c as F
The distribution function over the interval 2 x is
8
( ) ( ) 0 1, as (2) 1F x f x dx dx c F
Thus we have the probability distribution function defined as follows:
2
2
0 0
, 0 12
( )
2 1, 1 22
1 2
x
xx
F xx
x x
x
You can calculate mean, standard deviation and variance. Look at example 3.
Example 5. Show the following function is a probability distribution function
2
2
0 0
, 0 12
( )
2 1 1 22
1 2
x
xx
F xx
x x
x
Solution: We need to check the following properties:
a) Check that F is non-decreasing.
0 00, 0
, 0 1( ) 1 | 1|, 0 2
2 1 20, 2
0 2
xx
x xF x x x
x xx
x
shows that F is not decreasing.
b) For continuity check that 0 0
lim ( ) lim ( ) (0) 0x x
F x F x F and
2 2lim ( ) lim ( ) (2) 1x x
F x F x F
c) F is normalized: lim ( ) 0; lim ( ) 1x x
F x F x
The function F(x) defined above is probability distribution function.
Exercise:
1. For each of the following functions, i) find the constant c so that f (x) is a pdf of
the random variable X, ii) find the distribution function F(x) ( )P X x and iii)
sketch f (x) and F(x), iv) find also 2, , .
9
a) 3
( ) , 04
xf x x c
b) 23
( ) ,16
xf x c x c
c) ( ) 4 , 0 1cf x x x
d) ( ) , 0 4f x c x x
2. Sketch the graph of the following pdf f (x), then find and sketch the probability
distribution function F(x) on the real line. Review example 4.
a) 23
( ) , 1 12
xf x x
b) 1
( ) , 1 12
f x x
c) 1 , 1 0
( )1 , 0 1
x xf x
x x
Section 8.5 The Normal Distribution
A normal distribution of a random variable X with mean and variance 2 is a statistic
distribution with probability density function (pdf)
(1)
on the domain . While statisticians and mathematicians uniformly use the term
"normal distribution" for this distribution, physicists sometimes call it a Gaussian
distribution and, because of its curved flaring shape, social scientists refer to it as the
"bell curve."
De Moivre developed the normal distribution as an approximation to the binomial
distribution, and it was subsequently used by Laplace in 1783 to study measurement
errors and by Gauss in 1809 in the analysis of astronomical data (Havil 2003, p. 157).
10
The normal distribution is an extremely important probability distribution in many
fields. It is a family of distributions of the same general form, differing in their location
and scale parameters: the mean ("average") and standard deviation ("variability"),
respectively. The standard normal distribution is the normal distribution with a mean
of zero and a standard deviation of one (the green curve in the plots below). It is often
called the bell curve because the graph of its probability density resembles a bell.
If a random variable X has this distribution, we write ~ . If and , the
distribution is called the standard normal distribution and the probability density
function reduces to
Area under a normal curve:
For a standard normal variate z, the normal distribution has mean zero and standard
deviation one with pdf 22 / 21 1
( ) exp / 22 2
zf x z e
The area under the standard normal distribution curve for 21
( ) exp22
zu
f Z z du . We have now the difficulty to evaluate the integral
without having the knowledge of multivariable calculus and polar coordinate form. But
this difficulty we can manage using standard values from the table 5 of Normal
distribution at page # 423 or using our calculator. Look at example 3.
11
Important Information: All normal density curves satisfy the following property which
is often referred to as empirical rule:
1. 68.26% of the observations fall within 1 standard deviation of mean.
2. 95.44% of the observations fall within 2 standard deviation of mean
3. 99.74% of the observations fall within 3 standard deviation of mean
Note: Within 5 standard deviation of mean we assume 100% data points.
Example 1. Find the mean and standard deviation of the normal distribution whose pdf is
given as 21 ( 7)
( ) exp128128
xf x
Solution: Compare with the standard formula of pdf for the normal distribution and find
that 8, 7 .
Example 2. Write the pdf of a normal distribution with mean 3 and variance 16.
Solution: We have 4, 3 , the pdf of the normal distribution is given as
21 ( 3)( ) exp
324 2
xf x
Example 3. Find the area under the normal curve with mean zero and standard deviation
one for the standard variate 1.24z .
Solution: From table 5a:
( 1.24) 0.8925 89.25%P z
For this value choose row with 1.2 and column 0.04.
0 1.24
Using calculator: ( 1.24) 0.8925 89.25%P z
The calculator code:
2nd
DISTR 2 normalcdf (-5, 1.24) =0.8925120
Example 4. Find the area under the normal curve with mean zero and standard deviation
one for the standard variate 1.24z .
Solution: From table 5a:
( 1.24) 1 0.8925 10.75%P z
For this value choose row with 1.2 and column 0.04.
0 1.24
12
Using calculator: ( 1.24) 0.1075 10.75%P z
The calculator code: 2nd
DISTR 2 normalcdf ( 1.24, 5) =0.1074875
Example 5. Find the area under the normal curve with mean zero and standard deviation
one for 0.12 1.24z .
Solution: From table 5a:
( 0.12 1.24) ( .12) ( 1.24) 1 44.03%P z P z P z
-0.12 0 1.24
Using calculator: ( 0.12 1.24) 0.4402707 44.03%P z
The calculator code:
2nd
DISTR 2 normalcdf (-0.12, 1.24) =0.4402707
Example 6. Suppose x is a normally distributed random variable with mean 10.2 and
standard deviation 1.5. Find each of the following probabilities.
a) (6.1 13.3)P x .
b) (9.4 13)P x
c) (15.5 13.1)P x
d) ( 11.6)P x
e) ( 14.4)P x
Draw normal curve and show the region bounded by the normal curve and the x values.
Solution: from calculator a)
(6.1 13.3) 6.1,13.3,10.2,1.5 0.9774824 97.75%P x normalcdf
try similar way for b), and c),
d) 11.6 10.2
( 11.6) ,5 17.53%1.5
P x normalcdf
Try for e).
6.1 10.2 13.3
Exercise Set
1. The physical fitness of an athlete is often measured by how much oxygen the
athlete takes in (which is recorded in millimeters per kilogram, ml/kg). The
maximum oxygen uptake for elite athletes has been found to be 80 with a standard
deviation 9.2. Assume that distribution is approximately normal.
a) What is the probability that an elite athlete has a maximum oxygen uptake of
at least 75 ml/kg? Answer: 70.66%
13
b) What is the probability that an elite athlete has a maximum oxygen uptake of
65 ml/kg or lower? Answer: 5.15%
c) Consider someone with a maximum oxygen uptake of 26 ml/kg. Is it likely
that this person is an elite athlete? Answer: No
2. The combined score of SAT – 1 test are normally distributed with mean of 998
and a standard deviation of 202. If a college includes a minimum score of 800
among its requirements, what percentage of students do not satisfy that
requirement? Answer: 16.35%
3. IQ score are normally distributed with mean of 100 and a standard deviation 15.
Mensa is an international society that has one – and only one qualification for
membership, a score in the top 2 on an IQ test.
a) What IQ score should one have in order to be eligible for Mensa?
Answer: hint: (x-100)/15 = invnorm(0.98), x = 130.81
b) In a typical region of 90,000 people, how many are eligible for Mensa?
Answer: 90,000 (0.02) = 1800
4. Using diaries for many weeks, a study on the lifestyle of visually impaired
students was conducted. The students kept track of many lifestyle variables
including how many hours of sleep obtained on a typical day. Researchers found
that visually impaired students averaged 9.6 hours of sleep, with a standard
deviation of 2.56 hours. Assume that the number of hours of sleep for these
visually impaired students is normally distributed.
a) What is the probability that a visually impaired student gets less than 6.1
hours of sleep? Answer: 8.58%
b) What is the probability that a visually impaired student gets between 6.3 and
10.35 hours of sleep? Answer: 51.65%
c) Forty percent of students get less than how many hours of sleep on a typical
day? Answer: 8.95 hours
5. Healthy people have body temperatures that are normally distributed with a mean
of 98.20 degree Fahrenheit and a standard deviation of 0.62 degree Fahrenheit.
a) If a healthy person is randomly selected, what is the probability that he or she
has a body temperature above 98.9 degree Fahrenheit? Answer: 12.94%
b) A hospital wants to select a minimum temperature for requiring further
medical tests. What should that temperature be, if we want only 1% of healthy
people to exceed it? Answer: hint: (x-98.2)/.62 = invnorm(0.99), 99.64
6. The heights of a large group of people are assumed to be normally distributed.
Their mean height is 68 inches, and the standard deviation is 4 inches. What
percent of these people are taller than 73 inches? Answer: 10.56%
14
7. Suppose a population is normally distributed with a mean of 24.6 and a standard
deviation of 1.3. What percent of the data will lie between 25.3 and 26.8?
Answer: 24.91%