Class 3 Topics

• Simple probability
Contingency Tables
• Probability Distributions
The Normal Distribution

1
 Probability
Which of these are valid values for probability?
• 0.25
• 59
• 0.000002
• -0.94
• 4/5
• 5/4
Discuss
2
 Probability
Probability can be written as a fraction: e.g. ¼
or a decimal: e.g. 0.25
Probability must be between 0 and 1 inclusive
0 meaning it can not happen and 1 meaning it must/will happen
e.g. the probability of someone being 150 years old is zero

The sum of all probabilities of all possible outcomes of an event add up to 1

e.g. the probability of throwing a head or a tail when tossing a coin is 1
the probability of throwing a head = 0.5
the probability of throwing a tail = 0.5

3
 Probability
Which of these are valid values for probability?
• 0.25 - yes (between 0 and 1)
• 59 - no (more than 1)
• 0.000002 - yes (between 0 and 1)
• -0.94 - no (less than 0)
• 4/5 - yes (between 0 and 1)
• 5/4 - no (more than 1)

4
 Probability - Cards
With a partner answer these questions:
• How many cards are there in a standard pack
of cards?
• How many suits are there? What are they
called?
• How many colours are there? Which ones?
• How many cards are there of each suit? What
are they called?
5
 Probability - Cards
With a partner answer these questions:
• How many cards are there in a standard pack
of cards? 52
• How many suits are there? What are they
called? 4 (Hearts, diamonds, spades, clubs)
• How many colours are there? Which ones?
(Red, black)
• How many cards are there of each suit? What
are they called? Ace, 2 to 10, jack, queen, king
6
 Probability - Cards
With a partner answer these questions:
You randomly take a card from a standard pack of cards – what is
the probability of picking:
• A Queen?
• A red Queen?
• The Queen of hearts?
• A diamond?
• A Queen or a heart?

7
 Probability - Cards
With a partner answer these questions:
You randomly take a card from a standard pack of cards – what is
the probability of picking:
• A Queen? P = 1/13 (4/52)
• A red Queen? P = 1/26 (2/52)
• The Queen of hearts? P = 1/52
• A diamond? P = ¼ (13/52)
• A Queen or a heart? P(Queen)  P(heart )  P(Queen  heart )
p = 16/52 = 4/13 (4/52 + 13/52 – 1/52)

8
 Probability
With a partner answer these questions:
You roll a fair 6-sided die, what is the probability :
1. of rolling a 4?
2. of rolling greater than 4?
3. of rolling an odd number?

On two rolls of the same die, what is the probability:

a) of rolling 4 twice?
b) of rolling less than 4?
c) of rolling less than 11?
9
 Probability
With a partner answer these questions:
You roll a fair 6-sided die, what is the probability :
1. of rolling a 4? P(X=4) = 1/6
2. of rolling greater than 4? P(X>4) = 1/3
3. of rolling an odd number? P(X = odd number) = ½

On two rolls of the same die, what is the probability:

a) of rolling 4 twice?
b) of rolling less than 4?
c) of rolling less than 11?
10
 Probability
With a partner answer these questions:
You roll a fair 6-sided die, what is the probability :
1. of rolling a 4? P(X=4) = 1/6
2. of rolling greater than 4? P(X>4) = 1/3
3. of rolling an odd number? P(X = odd number) = ½

On two rolls of the same die, what is the probability:

a) of rolling 4 twice? 1/6 * 1/6 = 1/36
b) of rolling less than 4? (1+1, 1+2, 2+1) = 3/36 = 1/12
c) of rolling less than 11? (5+6, 6+5, 6+6) = 1 - (1/12) = 11/12
11
 Contingency Tables
200 people who had colds at an office were studied as to how long their cold lasted and
whether or not they took cold medicine. The results were recorded in the table below:
Medicine Taken
Yes No Total
Cold Length

1-3 days 86 19
4-7 days 16 79
Total

a. Calculate the probability that a randomly-chosen person:

i. took medicine
ii. Had a cold that lasted between 1 and 3 days and took medicine
iii. Had a cold that lasted 4-7 days given that s/he didn’t take any medicine
Step One: Find the totals

12
 Contingency Tables
200 people who had colds at an office were studied as to how long their cold lasted and
whether or not they took cold medicine. The results were recorded in the table below:
Medicine Taken
Yes (Y) No (N) Total
Cold Length

1-3 days (S) 86 19 105

4-7 days (L) 16 79 95
Total 102 98 200

a. Calculate the probability that a randomly-chosen person:

i. took medicine
ii. Had a cold that lasted between 1 and 3 days and took medicine
iii. Had a cold that lasted 4-7 days given that s/he didn’t take any medicine

13
 Contingency Tables
200 people who had colds at an office were studied as to how long their cold lasted and
whether or not they took cold medicine. The results were recorded in the table below:
Medicine Taken
Yes (Y) No (N) Total
Cold Length

1-3 days (S) 86 19 105

4-7 days (L) 16 79 95
Total 102 98 200

a. Calculate the probability that a randomly-chosen person:

i. took medicine P(Y) = 102/200 = 0.51

14
 Contingency Tables
200 people who had colds at an office were studied as to how long their cold lasted and
whether or not they took cold medicine. The results were recorded in the table below:
Medicine Taken
Yes (Y) No (N) Total
Cold Length

1-3 days (S) 86 19 105

4-7 days (L) 16 79 95
Total 102 98 200

a. Calculate the probability that a randomly-chosen person:

ii) Had a cold that lasted between 1 and 3 days and took medicine
P(Y86/200 = 0.43

15
 Contingency Tables
200 people who had colds at an office were studied as to how long their cold lasted and
whether or not they took cold medicine. The results were recorded in the table below:
Medicine Taken
Yes (Y) No (N) Total
Cold Length

1-3 days (S) 86 19 105

4-7 days (L) 16 79 95
Total 102 98 200

a. Calculate the probability that a randomly-chosen person:

iii. Had a cold that lasted 4-7 days given that s/he didn’t take any medicine

P ( L  N ) 79
P( L | N )    0.806
P( N ) 98

16
 Mutually Exclusive Events
Events are mutually exclusive if the occurrence of one
event excludes the occurrence of the other(s). Mutually
exclusive events cannot happen at the same time. For
example: when tossing a coin, the result can either be
heads or tails but cannot be both.

P( A  B)  0
P( A | B)  0

Think of some more examples of mutually exclusive events

17
 Mutually Exclusive Events
Examples of mutually exclusive events
• To have a British passport and a Japanese
passport (not so with Italian and Argentinian –
dual nationality)
• To drive a car and be blind (not true for
driving and texting at the same time)

P( A  B)  0
P( A | B)  0

18
 Independent Events
Events are independent if the occurrence of one event does
not influence (and is not influenced by) the occurrence of
the other(s). For example: when tossing two coins, the
result of one flip does not affect the result of the other.
You can prove independence with the following:

P( A  B)  P ( A) P ( B)
P( A | B )  P( A)

Think of some more examples of independent events

19
 Independent Events
Examples of independent events:
• Picking a King from two different decks of cards.
(not so with picking a king and then picking a king
from same deck of cards).
• The weather tomorrow is independent of whether
the date is odd or even.
• Your IQ is independent of the length of your hair.

P ( A  B)  P ( A) P ( B)
P ( A | B )  P( A)
20
 Contingency Tables
200 people who had colds at an office were studied as to how long their cold lasted and
whether or not they took cold medicine. The results were recorded in the table below:
Medicine Taken
Yes (Y) No (N) Total
Cold Length

1-3 days (S) 86 19 105

4-7 days (L) 16 79 95
Total 102 98 200

b. Are the events a person takes medicine and a person’s cold lasts 1-3 days
i. mutually exclusive? Why or why not?

ii. independent? Why or why not?

21
 Contingency Tables
200 people who had colds at an office were studied as to how long their cold lasted and
whether or not they took cold medicine. The results were recorded in the table below:
Medicine Taken
Yes (Y) No (N) Total
Cold Length

1-3 days (S) 86 19 105

4-7 days (L) 16 79 95
Total 102 98 200

b. Are the events a person takes medicine and a person’s cold lasts 1-3 days
i. Mutually exclusive?
P(Y  S )  86 / 200  0.43  0
therefore events Y and S are not mutually exclusive

ii. Independent?

22
 Contingency Tables
200 people who had colds at an office were studied as to how long their cold lasted and
whether or not they took cold medicine. The results were recorded in the table below:
Medicine Taken
Yes (Y) No (N) Total
Cold Length

1-3 days (S) 86 19 105

4-7 days (L) 16 79 95
Total 102 98 200

b. Are the events a person takes medicine and a person’s cold lasts 1-3 days
i. Mutually exclusive?
P (Y  S )  86 / 200  0.43  0
therefore events Y and S are not mutually exclusive
ii. Independent?
P(Y ) P( S )  102 / 200 *105 / 200  0.27 P(Y  S )  86 / 200  0.43
P(Y  S )  P(Y ) P( S )
therefore not independent events 23
BREAK TIME

24
 The Normal Distribution
• In probability theory, the normal distribution
is a very common continuous probability
distribution. Normal distributions are
important in statistics and are often used in
the natural and social sciences to represent
real-valued random variables whose
distributions are not known.
• The standard normal distribution is the most
important continuous probability distribution.
25
26
 Which of these populations are normally distributed?

1. The age of the students in this class

2. Score in a maths exam in a large university
3. The age of the population of Spain
4. The amount customers spend in a supermarket
5. How long it takes a shopper to buy an item online
6. IQ scores of students in a school year

Name some more populations that are

distributed in a bell shape

27
 Which of these populations are normally distributed?

1. The age of the students in this class (Yes)

2. Score in a maths exam in a large university (Yes)
3. The age of the population of Spain (No)
4. The amount customers spend in a supermarket (Yes)
5. How long it takes a shopper to buy an item online (No)
6. IQ scores of students in a school year (Yes)
Name some more populations that are distributed in a bell shape:
• Shoes sizes of customers in a store
• Heights of people in an airplane
• Cost of computers in FNAC

28
Populations

29
 The Normal Distribution
The normal distribution is completely symmetrical or bell shaped. The mean, mode
and median of this distribution all lie in the centre of the bell:

1. The curve is symmetrical about the mean.

2. The total area under the curve is equal to 1 or 100%: probability can be equated to area.
3. The horizontal axis represents a continuous variable such as weight.
4. The area under the curve between two points on the horizontal axis represents the
probability that the value of the variable lies between these two points.
5. The probability of a specific value is zero. It is only meaningful to talk about ranges .
6. The shape of the curve depends on the mean and standard deviation of the distribution.
As the standard deviation gets larger, the curve will get flatter and extend further on
either side of the mean.
30
 The Normal Distribution
• A problem
The average weight of a standard loaf of bread is
800g and the weights are normally distributed. If
a loaf is selected at random, what is the
probability that will weigh less than 800g?

31
 The Normal Distribution
• A problem
The average weight of a standard loaf of bread is
800g and the weights are normally distributed. If
a loaf is selected at random, what is the
probability that will weigh less than 800g? 0.5

32
The Normal Distribution

33
 The Normal Distribution
A Typical Question
A batch of loaves is baked. The weight of the loaves is normally
distributed with a mean of 800g and a standard deviation of 10g.
What is the probability that a loaf selected at random will weigh
more than 815g?

34
 The Normal Distribution
All normal distributions have a mean (µ) and
standard deviation (σ)
So we can standardise the normal distribution:
X 
z

so that is has a mean of 0 and a standard
deviation of 1

35
The Normal Distribution

36
37
 The Normal Distribution
All normal distributions have a mean (µ) and
standard deviation (σ)
So we can standardise the normal distribution:
X 
z

so that is has a mean of 0 and a standard
deviation of 1
In order to read the values off the table
38
 The Normal Distribution
First Draw it!
A batch of loaves is baked. The weight of the
loaves is normally distributed with a mean of
800g and a standard deviation of 10g. What is
the probability that a loaf selected at random
will weigh less than 815g?

39
 The Normal Distribution
First
A batch of loaves is baked. The weight of the
loaves is normally distributed with a mean of
800g and a standard deviation of 10g. What is
the probability that a loaf selected at random
will weigh less than 815g?

Ans: 0.93 (to2dp)

40
 The Normal Distribution
First
A batch of loaves is baked. The weight of the
loaves is normally distributed with a mean of
800g and a standard deviation of 10g. What is
the probability that a loaf selected at random
will weigh less than 815g? 0.9332
Another way to ask the question is:
What proportion of loaves will weigh less than
815g?
41
 The Normal Distribution
First
A batch of loaves is baked. The weight of the
loaves is normally distributed with a mean of
800g and a standard deviation of 10g. What is
the probability that a loaf selected at random
will weigh less than 815g? 0.9332
Another way to ask the question is:
What proportion of loaves will weigh less than
815g? 93.3%
42
 The Normal Distribution
Next:
A batch of loaves is baked. The weight of the
loaves is normally distributed with a mean of
800g and a standard deviation of 10g. What is
the probability that a loaf selected at random
will weigh more than 815g?
Or
What proportion of loaves will weigh more than
815g?
43
 The Normal Distribution
Next:
A batch of loaves is baked. The weight of the
loaves is normally distributed with a mean of
800g and a standard deviation of 10g. What is
the probability that a loaf selected at random
will weigh more than 815g? 1 – 0.9332 = 0.0668
Or
What proportion of loaves will weigh more than
815g? 6.68%
44
 The Normal Distribution
1. A loaf is chosen at random. What is the
probability that the weight will lie between
810g and 812g?
2. What proportion of loaves weigh between
790g and 805.5g?
Remember to draw it first!

45
 The Normal Distribution
1. A loaf is chosen at random. What is the
probability that the weight will lie between 810g
and 812g?
0.0436
2. What proportion of loaves weigh between 790g
and 805.5g?
55.01%

46
 Covered Today
Probability
Contingency Tables
Probability Distributions
The Normal Distribution

47
 Homework
Worksheet on:
Probability Distributions
The Normal Distribution

48