Professional Documents
Culture Documents
𝑃 ( 𝑥=4)
𝑥 ≤ 3) 𝑃 (𝑥= 𝑋 )
The probability of getting 4 heads will
The probability of getting 3 heads or
be equal to the height of this bar
less will be equal to the sum of the
heights of these bars
0 1 2 3 4 5 6 7 8
The normal distribution
For a quantity such as height, the majority of people will be close to the average
As we move further away from the average height, there are fewer people
ie – there would be a lower probability of randomly selecting one at that height
The shape
If weofreduce
the Histogram becomes
the classwidths smoother. If
used…
we continue indefinitely, we get what is known as
the normal distribution curve…
The normal distribution
For a quantity such as height, the majority of people will be close to the average
As we move further away from the average height, there are fewer people
ie – there would be a lower probability of randomly selecting one at that height
2
𝑁 (𝜇 , 𝜎 )
It is symmetrical, so mean = median = mode
So what would
For this area be?
Area
= 0.68
.16
a =0
Are
𝐻
The normal distribution
Approximately 95% of the data is
within 2 standard deviations of the
mean
For
Area
= 0.95
𝐻
The normal distribution
Almost all (99.7%) of the data is within 3
standard deviations of the mean
For
Area = 0.997
𝐻
The normal distribution
EXAMPLE 175cm
The heights of males in a city, Xcm, are modelled
as X~N(175, 144)
a)
b)
c)
3A
Exercise 3A – Page 40
The normal distribution
The lengths of a colony of adders, Ycm, are modelled as Y~N(100,).
If 68% of the adders have a length between 93cm and 107cm, find .
Exercise 3A – Page 40
Finding probabilities for normal
distributions
Now, on your calculator, press
menu
𝜇=30
You need to be able to use the
normal cumulative distribution
𝜎 =4
function on your calculator to
find probabilities Now press 7 for distributions
Press equals and the calculator will tell you the area!
3B
Finding probabilities for normal
distributions
𝜇=30
You need to be able to use the
normal cumulative distribution
𝜎 =4
function on your calculator to
find probabilities
3B
Finding probabilities for normal
distributions
𝜇=30
You need to be able to use the
normal cumulative distribution
𝜎 =4
function on your calculator to
find probabilities
Press equals and the calculator will tell you the area
Even though we will use your
calculator, we should still sketch
the situation…
3B
Finding probabilities for normal
distributions
𝜇=30
You need to be able to use the
normal cumulative distribution
𝜎 =4
In this case, we can find the
function on your calculator to area between 27 and 32, and
find probabilities then subtract it from 1…
a) ¿ 0.773 3
Now input the limits,
b) ¿ 0.9331 mean and standard
c) ¿ 0.1706 deviation
d) ¿ 0.5352
Press equals
¿ 0.4648
Even though we will use your
calculator, we should still sketch In this case, remember
that you need to subtract
the situation… the answer from 1…
3B
Finding probabilities for normal
distributions
You need to be able to use the Use your calculator as before. The lower limit should be
normal cumulative distribution 140, the upper limit should be at least 175 (5 times the
function on your calculator to standard deviation above the mean).
find probabilities
The mean is 100 and the standard deviation is 15…
3B
Statistical Distributions
With a number of trials, , and a
probability of success,
If is binomially
distributed
𝑋 𝐵 (𝑛, 𝑝)
The Binomial Distribution
𝑋 𝐵 (𝑛, 𝑝), then:
If
Probability of
failure to the power
𝑃 ( 𝑋 =𝑟 ) =
( )
𝑛
𝑟
𝑟
𝑝 (1 −𝑝 )
𝑛− 𝑟
probabilities:
() ( ) ( )
2 3
( ) 5 2 1
𝑃 𝑋 =2 = × ×
2 3 3
a)
40
¿ 𝑜𝑟 0.165 (3 𝑠 . 𝑓 )
b) 243
c)
The Binomial Distribution
The random variable . Find:
a)
b)
c)
6B
The random variable . Find:
a)
b)
c)
d)
The normal distribution
For this part you will need to use what you learned in year 12
You need to be able to use the (the binomial distribution)
normal cumulative distribution
function on your calculator to There are 20 adults in the sample, and the probability of a
find probabilities genius is 0.00383
Area = 0.75
will give specific probabilities
Now press 7 for distributions
3C
Inverse normal distribution
𝜇=20
You also need to be able to use
the inverse function on you
𝜎 =3
calculator, to find values that
will give specific probabilities
Area =
0.4
Draw a sketch to get an idea of where After putting the mean and standard deviation in as well, the
the value should be calculator will tell you the value…
3C
Inverse normal distribution
𝜇=20
You also need to be able to use
the inverse function on you
𝜎 =3
calculator, to find values that Area =
will give specific probabilities 0.3
Area =
0.0912
Given that find, to two decimal places,
the values of such that: 16𝑎20
c)
¿ 20.76 using the function on your calculator
we used in section 3B
¿ 19.17
It is 0.0912…
Draw a sketch to get an idea of where
the value should be
So put in an area of 0.3912, as well
as the mean and standard deviation, in
order to find the value
3C
Inverse normal distribution
𝜇=20
You also need to be able to use
the inverse function on you
𝜎 =1.5
calculator, to find values that
Area = 0.6
will give specific probabilities
3C
Inverse normal distribution
𝜇=20
You also need to be able to use
the inverse function on you
Area =
0.25
𝜎 =1.5
Area =
calculator, to find values that 0.25
will give specific probabilities
Area = Area =
0.25 0.25
Plates made using a particular
manufacturing process have a 𝐿𝑄 20 𝑈𝑄
diameter, , which can be modelled using
a normal distribution, . Firstly, remember that for normally distributed
data, Mean = Median = Mode, so the value of 20 is
also the Median
a) Given that 60% of plates are less
than , find the value of .
Secondly, remember that the quartiles and the
¿ 20.38 𝑐𝑚 median split the data into 4 equal parts, with the
same quantity of data in each
b) Find the interquartile range of the
plate diameters
Therefore, the area below the lower quartile (and
all the other areas), will be 0.25
3C
Inverse normal distribution
𝜇=20
You also need to be able to use
the inverse function on you
𝜎 =1.5
calculator, to find values that
will give specific probabilities
Area =
0.25
Plates made using a particular
manufacturing process have a 𝐿𝑄 20 𝑈𝑄
18.988 21.011
diameter, , which can be modelled using 1.011 1.011
a normal distribution, . So find the value that has an area of 0.25 less that
it, using your calculator as before.
a) Given that 60% of plates are less You should get 18.988…
than , find the value of .
¿ 20.38 𝑐𝑚 Subtract this value from 20 to find the distance
between the LQ and the Median
b) Find the interquartile range of the
plate diameters
You should get 1.011
3C
Inverse normal distribution
𝜇=20
You also need to be able to use
the inverse function on you
𝜎 =1.5
calculator, to find values that
will give specific probabilities
Area =
0.25
Plates made using a particular
manufacturing process have a 18.988 20 21.011
diameter, , which can be modelled using
a normal distribution, . So the interquartile range will be the difference
between the two values we calculated
a) Given that 60% of plates are less This is equal to 2.02, to 2dp
than , find the value of .
¿ 20.38 𝑐𝑚 (note that we could also find the difference between
the Median and the LQ, and just double that!)
b) Find the interquartile range of the
plate diameters
¿ 2.02 𝑐𝑚
3C
Teachings for
Exercise 3D
The normal distribution
𝜇=25
You need to be able to use the
standard normal distribution. If 𝜎 =3
you need to work out an unknown Let
mean or standard deviation, you
will need to use this…
A set of normally distributed data can The coding will change all 25 31
be coded so it fits the standard normal values in the same way, such
distribution that the mean becomes 0 and
the standard deviation
3D
𝑋 −𝜇
𝑍=
𝜎
𝑋 −𝜇
𝑍=
𝜎
3D
𝑋 −𝜇
𝑍=
𝜎
3D
𝑋 −𝜇
𝑍=
𝜎
𝑧 =0.75
This is telling us that when we code the original data set to
the standardized one, a value of will become
a)
¿ Φ (0.75)
𝜇=0
If we compare the diagram for the
𝜎 =1
original distribution, and the new one, Standardised
the probability of getting below 53 on
the first is the same as the probability
of getting below 0.75 on the second
3D
𝑋 −𝜇
𝑍=
𝜎
𝑧 =1.25
The random variable . Write in terms of
for some value :
This is telling us that when we code the original data set to
the standardized one, a value of will become
b)
Therefore:
Remember we
𝑃 ( 𝑋 ≥ 53 ) =𝑃 ( 𝑍 ≥ 1.25) would need to
use the area
below the value
¿ 1 − 𝑃 ( 𝑍 <1.25) given
¿ 1 −Φ (1.25)
3D
𝑋 −𝜇
𝑍=
𝜎
Area = 0.3
0?
0.5244
3D
𝑋 −𝜇
𝑍=
𝜎
0 ?
Start by drawing a sketch for the
original distribution, and the
standardised one…
3D
𝑋 −𝜇
𝑍=
𝜎
Area =
0.05
0 1.6449
?
Now we need to use the formula in
reverse. We have the value of and
want the corresponding value of
3D
Teachings for
Exercise 3E
𝑋 −𝜇
𝑍=
𝜎
3E
𝑋 −𝜇
𝑍=
𝜎
3E
𝑋 −𝜇
𝑍=
𝜎
𝜎 =5.00 (3 𝑠𝑓 )
b) Find the 90th percentile of the
widths
3E
𝑋 −𝜇
𝑍=
𝜎
2
𝑍 𝑁 (0 , 1 )
Find the two values for in the
standard distribution diagram. You Upper tail 𝜇=0
can use the table of values for the 𝜎 =1
𝑥 −𝜇
upper tail, and the inverse function 𝑧=
on your calculator for the lower tail… 𝜎
Sub in
35 −𝜇 values Area = Area =
1.96= 0.1469 0.025
𝜎
Then use the formula above with Multiply
each of these… by ? 0
−1.05 1.96
?
1.96 𝜎=35 − 𝜇
3E
𝑋 −𝜇
𝑍=
𝜎
2) 1.96 𝜎=35 − 𝜇
The random variable . Given that and ,
find the values of and . 2) - 1)
3.01 𝜎 =20
Now we have 2 equations, we can Divide by 3.01
solve them simultaneously 𝜎 =6.64 Use this value to find
the mean
𝜇=22.0
3E
Teachings for
Exercise 3F
𝑋 −𝜇
𝑍=
𝜎
You can use the processes you have learnt for the normal distribution to approximate a binomial
distribution under 2 conditions
The value of (the number of trials) must be ‘large’ (this will mean the distribution is smoother)
The probability of success must be close to 0.5 (if it is not, then the distribution will not be
symmetrical)
3F
𝑋 −𝜇 Using normal distribution to must be large
𝑍= approximate a binomial distribution must be close to 0.5
𝜎
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
∑𝑥
𝑛 ¿ ∑ 𝑥 ×𝑝 (𝑥)
❑
Multiply each outcome by its
Add all the outcomes up, and divide by probability, and then add them all
how many there are in total up after
(note that in the example we used , but So really it is
the idea is the same – add up all the
values! The fx just sped things up a bit)
3F
∑𝑥 𝑋 𝐵 (𝑛, 𝑝)
𝑛 ¿ ∑ 𝑥 ×𝑝 (𝑥) 𝑋 𝑁 (𝜇, 𝜎)
∑ 𝑓 𝑥 =910
were all instead of … 2
𝑛=60
Mean of =
Sub in values
Mean of =
Calculate
Mean of =
3F
∑𝑥 𝑋 𝐵 (𝑛, 𝑝)
𝑛 ¿ ∑ 𝑥 ×𝑝 (𝑥) 𝑋 𝑁 (𝜇, 𝜎)
∑ 𝑥 ×𝑝 ( 𝑥 ) =15.16…
2
3F
∑𝑥 ∑ 𝑥2 𝑋 𝐵 (𝑛, 𝑝)
𝑛 ¿ ∑ 𝑥 ×𝑝 (𝑥) 𝑛 ¿ ∑ 𝑥2 ×𝑝 (𝑥) 𝑋 𝑁 (𝜇, 𝜎)
∑𝑥 2
𝑛 ¿ ∑ 𝑥 ×𝑝 (𝑥)
2
❑
Multiply each squared outcome by
Add all the squared outcomes up, and its probability, and then add
divide by how many there are in total them all up after
So really it is
3F
∑𝑥 ∑ 𝑥2 𝑋 𝐵 (𝑛, 𝑝)
𝑛 ¿ ∑ 𝑥 ×𝑝 (𝑥) 𝑛 ¿ ∑ 𝑥2 ×𝑝 (𝑥) 𝑋 𝑁 (𝜇, 𝜎)
∑ ∑𝑥
( )
2 2
You need to be able to approximate 2 𝑥 The second part of this is
𝜎 = − the mean squared
a binomial distribution 𝑛 𝑛
Remember that we
already have an expression
Can you remember the formula for the 𝜎
2
=
∑ 𝑥
2
− ( 𝑛𝑝 )
2 for the mean from before!
variance of a data set from year 12? 𝑛
∑ (𝑥 ×𝑝(𝑥))
2 We can replace the first part using the equivalent
calculation that we saw before…
𝜎
2
=
∑ 𝑥
2
− ( 𝑛𝑝 )
2
𝑛
Replace first term
using the above
𝜎 =∑ (𝑥 ×𝑝(𝑥))− ( 𝑛𝑝 )
2 2 2
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
You need to be able to approximate Imagine we are considering the number of heads when
a binomial distribution tossing a biased coin 5 times. Let , and
∑ (𝑥 ×𝑝(𝑥))
2 2
3
(52) 0.4 ( 0.6 ) 2 × (52 ) 0.4 ( 0.6 )
2 3 2
( () )
𝑛 3 2 2 3 2
∑ 𝑥2 × 𝑛 𝑝
Remember how
𝑥 to find
( 1 −𝑝 ) the
𝑛− 𝑥
¿
calculation for
𝑥 a an event that is
𝑥=0
binomially distributed? 4 ( 54 ) 0.4 ( 0.6 ) 4 × (54 ) 0.4 ( 0.6 )
4 1 2 4 1
(We
𝑃 ( 𝑋will
=𝑟
( )
be) =
from up
𝑛
summing
𝑝 the
𝑟
𝑟 to …)
values
(1 − 𝑝)
𝑛− 𝑟
2
𝑥 ×
(𝑛𝑥 ) 𝑝 𝑥
( 1 − 𝑝 )𝑛 −𝑥
So we are doing this calculation for each value of , and then adding them up…
3F
( )
𝑃 ( 𝑋 =𝑟 ) = 𝑛 𝑝 𝑟 ( 1 − 𝑝 )𝑛 − 𝑟
𝑟
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
You need to be able to approximate You hopefully also remember the following from
a binomial distribution year 12 (Binomial expansion powerpoint)
( () )
𝑛
¿ ∑ 𝑥2 × 𝑛 𝑝 𝑥 ( 1 −𝑝 )
𝑛− 𝑥
( )
𝑛
𝑛!
¿ ∑ 𝑥2 ×
𝑛− 𝑥
𝑝 𝑥 ( 1 −𝑝 )
𝑥=0 ( 𝑛− 𝑥 ) ! 𝑥 !
Group
together
( )
𝑛 𝑥 𝑛− 𝑥
𝑛! 𝑝 ( 1 −𝑝 )
¿∑
2
𝑥 ×
𝑥=0 ( 𝑛 − 𝑥) ! 𝑥 !
3F
( )
𝑃 ( 𝑋 =𝑟 ) = 𝑛 𝑝 𝑟 ( 1 − 𝑝 )𝑛 − 𝑟
𝑟
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
( )
𝑛 𝑥 𝑛− 𝑥
You need to be able to approximate 𝑛 ! 𝑝 ( 1 −𝑝 )
a binomial distribution
∑ 2
𝑥 ×
( 𝑛− 𝑥 ) ! 𝑥 !
The first term will be when
𝑥 =0
This first term will therefore
be 0, due to the part, so we do
not need to include it in the
Can you remember the formula for the summation…
variance of a data set from year 12?
( )
𝑛
𝑛 ! 𝑝 𝑥 ( 1− 𝑝 )𝑛− 𝑥 Therefore, we can start the
∑ 2
𝑥 ×
(𝑛− 𝑥 )! 𝑥 ! summation from instead…
𝑥 =1
( )
𝑛 𝑥 𝑛− 𝑥
𝑛! 𝑝 ( 1 −𝑝 )
¿∑
2
𝑥 × This term is
𝑥=0 ( 𝑛 − 𝑥) ! 𝑥 !
We can ‘cancel’ one of the first terms with the from
this factorial…
( )
𝑛 𝑥 𝑛− 𝑥
𝑛 ! 𝑝 ( 1 −𝑝 )
¿∑ 𝑥×
𝑥=1 ( 𝑛 − 𝑥 ) ! ( 𝑥 − 1) !
3F
( )
𝑃 ( 𝑋 =𝑟 ) = 𝑛 𝑝 𝑟 ( 1 − 𝑝 )𝑛 − 𝑟
𝑟
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
( )
𝑛 𝑥 𝑛− 𝑥
𝑛 ! 𝑝 ( 1 −𝑝 )
You need to be able to approximate ¿ ∑ 𝑥× summation of a number of
a binomial distribution 𝑥=1 ( 𝑛 − 𝑥 ) ! ( 𝑥 − 1) ! terms
( )
𝑛 𝑥 𝑛− 𝑥
𝑛! 𝑝 ( 1 −𝑝 )
¿∑
2
𝑥 ×
𝑥=0 ( 𝑛 − 𝑥) ! 𝑥 ! The term has been adjusted as well…
So
( )
𝑛 𝑥 −1 𝑛 −𝑥
(𝑛 − 1) ! 𝑝 ( 1− 𝑝 )
You need to be able to approximate 𝑛𝑝 ∑ 𝑥×
(𝑛 − 𝑥 ) !( 𝑥 − 1) ! This will affect most
a binomial distribution
𝑥=1
terms
We will now be
starting on instead of
Can you remember the formula for the
variance of a data set from year 12? We have not changed
the number of terms
though, so the final
term will now be
( )
𝑛− 1 𝑦 𝑛− 𝑦 − 1
So now we need to rewrite this… (𝑛 −1)! 𝑝 ( 1 −𝑝 )
𝑛𝑝 ∑ ( 𝑦 +1)×
( 𝑛 − 𝑦 −1 ) ! (𝑦 )!
( )
𝑛 𝑥 𝑛− 𝑥 𝑦=0
𝑛! 𝑝 ( 1 −𝑝 )
¿∑
2
𝑥 ×
𝑥=0 ( 𝑛 − 𝑥) ! 𝑥 !
3F
( )
𝑃 ( 𝑋 =𝑟 ) = 𝑛 𝑝 𝑟 ( 1 − 𝑝 )𝑛 − 𝑟
𝑟
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
( )
𝑛− 1 𝑦 𝑛− 𝑦 − 1
(𝑛 −1)! 𝑝 ( 1 −𝑝 )
𝑛𝑝 ∑ ( 𝑦 +1)×
𝑦=0 ( 𝑛 − 𝑦 −1 ) ! (𝑦 )!
We can write this as two
separate summations (using
[ ]
𝑛−1 𝑦 𝑛− 𝑦 −1 𝑛− 1 𝑦 𝑛− 𝑦 −1 the
(𝑛− 1)!𝑝 (1 −𝑝 ) (𝑛−1)!𝑝 ( 1 −𝑝 )
¿ 𝑛𝑝 ∑ 𝑦 × +∑
𝑦= 0 ( 𝑛− 𝑦 −1 ) !( 𝑦)! 𝑦 =0 ( 𝑛− 𝑦 − 1 ) !(𝑦 )!
()𝑛
𝑟
=
𝑛!
(𝑛 − 𝑟 ) ! 𝑟 ! What if we let and ?
( 𝑛 −1
𝑦
=¿
) (𝑛 − 1) !
( 𝑛− 𝑦 −1 ) ! 𝑦 !
[ ]
𝑛−1 𝑛− 1
𝑦= 0 𝑦 ( )
¿ 𝑛𝑝 ∑ 𝑦 × 𝑛−1 𝑝 𝑦 ( 1 −𝑝 )
𝑛− 𝑦 − 1
+ ∑ 𝑛−1 𝑝 𝑦 ( 1 −𝑝 )
𝑦=0 𝑦 ( )
𝑛− 𝑦 − 1
3F
( )
𝑃 ( 𝑋 =𝑟 ) = 𝑛 𝑝 𝑟 ( 1 − 𝑝 )𝑛 − 𝑟
𝑟
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
[∑ ]
𝑛−1 𝑛−1
𝑛𝑝
𝑦=0
( )
𝑦 × 𝑛−1 𝑝 𝑦 ( 1− 𝑝 )
𝑦
𝑛− 𝑦 − 1
𝑦 =0 𝑦( )
+ ∑ 𝑛−1 𝑝 𝑦 ( 1− 𝑝 )
𝑛− 𝑦 −1
Lets think about the second summation, using heads on the biased coin from before as an example
( )
2
0
0
0.4 0.6
2
+¿( ) 2 0.4 1 0.61
1 +¿( )
2 0.4 2 0.60
2
What will these add up to?
They will add up to 1 as they represent all possible outcomes (from 2 choose 0 + from 2
choose 1 + from 2 choose 2)
3F
( )
𝑃 ( 𝑋 =𝑟 ) = 𝑛 𝑝 𝑟 ( 1 − 𝑝 )𝑛 − 𝑟
𝑟
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
[∑ ]
𝑛−1 𝑛−1
𝑛𝑝
𝑦=0
( )
𝑦 × 𝑛−1 𝑝 𝑦 ( 1− 𝑝 )
𝑦
𝑛− 𝑦 − 1
𝑦 =0
( )
+ ∑ 𝑛−1 𝑝 𝑦 ( 1− 𝑝 )
𝑦
𝑛− 𝑦 −1
[ ]
𝑛−1 part represents the probability of each
𝑛𝑝 ∑ 𝑦 × (𝑛−1
𝑦 )
𝑝 𝑦
( 1− 𝑝 )
𝑛− 𝑦 − 1
+1 value of happening
𝑦=0
ie) We can rewrite this as
[∑ ]
𝑛−1 The only difference is that the number
𝑛𝑝 𝑦 ×𝑝 ( 𝑦 ) +1 of terms is , which is accounted for in
𝑦=0 the summation term
𝑃 ( 𝑋 =𝑟 ) =
( 𝑛𝑟) 𝑝 𝑟
( 1 − 𝑝 )𝑛 − 𝑟
3F
( )
𝑃 ( 𝑋 =𝑟 ) = 𝑛 𝑝 𝑟 ( 1 − 𝑝 )𝑛 − 𝑟
𝑟
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
[∑ ]
𝑛−1
This term is saying to multiply all the possible values of by
𝑛𝑝 𝑦 ×𝑝 ( 𝑦 ) +1 their probabilities, and then add the answers up
𝑦=0
What does that give us?
3F
( )
𝑃 ( 𝑋 =𝑟 ) = 𝑛 𝑝 𝑟 ( 1 − 𝑝 )𝑛 − 𝑟
𝑟
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
∑
( )
∑𝑥
2 2
You need to be able to approximate 2 𝑥
𝜎 = −
a binomial distribution 𝑛 𝑛
Earlier, we replaced
the mean with
Multiply the
The expression we just found is that: inner bracket
𝜎 2=𝑛𝑝 [ 𝑛𝑝 − 𝑝+ 1 ] − ( 𝑛𝑝 )2
Multiply the
𝑛𝑝 [ ( 𝑛− 1 ) 𝑝 +1 ] square bracket
𝜎 2=( 𝑛𝑝 )2 − 𝑛 𝑝 2 +𝑛𝑝 − ( 𝑛𝑝 )2
Simplify
A reminder that we were finding 2
𝜎 =𝑛 𝑝 −𝑛𝑝
2
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
¿ 0 .4032
b) Also use the approximation to find
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
( )
𝑃 ( 𝑌 =𝑟 ) =
𝑛
𝑟
𝑟
𝑝 (1 −𝑝 )
𝑛− 𝑟
Sub in values, with
the number of yellow
For a particular type of flower bulb, bulbs being 30
55% will produce yellow flowers. A
random sample of 80 bulbs is planted. ( )
𝑃 ( 𝑌 =50 ) =
80
50
50
0.55 ( 0.45 )
30
Calculate
𝑃 ( 𝑌 =50 ) =0.0365
Calculate the percentage error
incurred when using a normal
approximation to estimate the
probability that there are exactly 50
yellow flowers.
𝑃 ( 𝑌 =50 ) =0.0365
First, calculate the actual
probability using the binomial
distribution
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
3F
𝑋 𝐵 (𝑛, 𝑝)
𝑋 𝑁 (𝜇, 𝜎)
3F
Teachings for
Exercise 3G
The normal distribution
You need to be able to do hypothesis
testing using the normal distribution
1 2 3 4 4 5 5 6
6 6 7 7 8 8 9 10 11
For this data, the information is as In this case, the data set is so small that we can
follows: include all the data
3G
The normal distribution
Imagine we took samples from this data, all of
You need to be able to do hypothesis
testing using the normal distribution size 2 (ie – choosing 2 values at random)
For example:
Imagine we had a set of data as follows:
Value 1 Value 2 Mean
4 5 4.5
1 2 3 4 4 5 5 6
3 9 6
6 6 7 7 8 8 9 10 11
6 5 5.5
2
𝑋 𝑁 (6 ,2.65 ) 2 8 5
7 10 8.5
Notation for the population 6 8 7
Notation for this sample Let’s now calculate the mean and variance of this
data set…
2
Sample mean = 6.08
𝑋 𝑁 (6.08 , 1.33 ) Variance (of the sample means) = 1.78
Standard Deviation (of the sample means) = 1.33
3G
The normal distribution
Imagine we took samples from this data, all of
You need to be able to do hypothesis
testing using the normal distribution size 2 (ie – choosing 2 values at random)
For example:
Imagine we had a set of data as follows:
Value 1 Value 2 Mean
4 5 4.5
1 2 3 4 4 5 5 6
3 9 6
6 6 7 7 8 8 9 10 11
6 5 5.5
2
𝑋 𝑁 (6 ,2.65 ) 2 8 5
7 10 8.5
Notation for the population 6 8 7
Notation for this sample
If we take enough samples, then because the data
is normally distributed, the sample mean will
2 average out to be the same as the population
𝑋 𝑁 (6.08 , 1.33 ) mean
Sample size 2 range: If we took a sample size 10, the smallest possible
mean would be 4.2, and the largest would be 7.8
1.5-10.5
2
𝑋 𝑁 (𝜇 , 𝜎 )
𝑋 𝑁 𝜇, (
𝜎2
𝑛 )
We divide the population
variance by the sample size,
3G
2
𝑋 𝑁 (𝜇 , 𝜎 )
𝐻 0 :𝜇=60
You need to be able to do hypothesis
testing using the normal distribution 𝐻 1 : 𝜇<60
(
𝑋 𝑁 60 ,
32
16 )
A company sells fruit juice in cartons. The 3) Now, using the sample distribution, we need to find
amount of juice in a carton has a normal the probability that a random sample of 16 gives a
distribution with a standard deviation of 3ml. mean equal to or lower than 59.1…
𝐻 0 :𝜇=60
You need to be able to do hypothesis
testing using the normal distribution 𝐻 1 : 𝜇<60
(
𝑋 𝑁 60 ,
32
16 )
A company sells fruit juice in cartons. The
amount of juice in a carton has a normal
distribution with a standard deviation of 3ml.
𝑃 ( 𝑋 < 59.1 )=0.1151
¿ 11.51 %
The company claims that the mean amount of
juice per carton, , is 60ml. A trading
Although getting in this range is unlikely , it is not
inspector has received complaints that the
below 5%
company is overstating the amount of juice
per carton and wishes to investigate this
Therefore, it is not unlikely enough for us to
complaint.
reject the null hypothesis that the mean is
actually 60ml
The inspector takes a random sample of 16
cartons and finds that the mean amount of So we accept the null hypothesis
juice per carton is 59.1ml.
Population Sample
Variance
Variance
( )
2
𝑋 𝑁 (𝜇 , 𝜎 )
2 𝜎
𝑋 𝑁 𝜇,
𝑛
Converting values to Converting values to
the standard normal Square the standard normal Square
distribution root the distribution root the
variance variance
𝑋 −𝜇 𝑋 −𝜇
𝑍= 𝑍=
𝜎 𝜎
Standard √𝑛
deviation Standard
deviation
3G
𝑋 𝑁 (𝜇 , 𝜎 )
2
𝑋 −𝜇
𝑍=
𝜎
3G
𝑋 𝑁 (𝜇 , 𝜎 )
2
𝑋 −𝜇
𝑍=
𝜎
Remember that the critical region is the Area = Area = Due to symmetry, the lower
region where the null hypothesis would be 0.005 0.005 value will be the negative of
rejected… this…
? 0 2.5758
−2.5758 ?
3G
𝑋 𝑁 (𝜇 , 𝜎 )
2
𝑋 −𝜇
𝑍=
𝜎
𝐻 0 :𝜇=0.580 𝐻 1 :𝜇 ≠ 0.580
You need to be able to do hypothesis
testing using the normal distribution
Since this mean is inside the critical region,
A machine produces bolts of diameter where
there is sufficient evidence to reject the null
has a normal distribution with mean 0.580cm
hypothesis
and standard deviation 0.015cm.
It seems that the mean diameter has
changed…
This machine is serviced and after the service
a random sample of 50 bolts from the next
production is taken to see if the mean
diameter of the bolts has changed from
0.580cm. The distribution of the bolts after
the service is still normal with a standard
deviation of 0.015cm.
or
b) The mean diameter of a sample of 50
bolts is found to be 0.587mm. Comment
on this in light of the critical region
3G