Lesson 2 Theory
Lesson 2 Theory
Need of the human being to describe, analyze and synthesize search for techniques
in order to satisfy this necessity
STATISTICAL TECHNIQUES
Types of phenomena
Deterministic phenomenon
This phenomenon satisfies that when it is repeated several times and under
identical conditions, always provides with the same result.
Random phenomena entail uncertainty and they are the subject under study in
Statistics.
As we cannot know the result of the random phenomenon beforehand it
generates uncertainty to the researcher need to measure uncertainty a value
______________________________________________________________________
Degree in Economics / Estefana Mourelle Espasandn 2016/2017
Lesson 2. Probability. Introduction to Probability Calculus Statistics I ~2~
______________________________________________________________________
Sample space
It is associated with any random experiment (for instance, throwing dice). The set
of all basic outcomes from a random experiment is called the sample space.
Definitions
Elementary event: each one of the possible outcomes from a random experiment
basic outcomes.
Sample space (): set of all basic outcomes from a random experiment.
Event (E): any subset of basic outcomes from the sample space.
Complement of event E (
): set of basic outcomes of a random experiment
______________________________________________________________________
Degree in Economics / Estefana Mourelle Espasandn 2016/2017
Lesson 2. Probability. Introduction to Probability Calculus Statistics I ~3~
______________________________________________________________________
Union of events
Let A and B be two events in the sample space . Their union, A B, occurs if
and only if either A or B or both occur. That is,
A, B A B = { x x A or x B}
Intersection of events
A, B A B = { x x A and x B}
Events A and B are mutually exclusive when they have no common basic outcomes, so
their intersection is the empty set: A, B A B = .
Definition
______________________________________________________________________
Degree in Economics / Estefana Mourelle Espasandn 2016/2017
Lesson 2. Probability. Introduction to Probability Calculus Statistics I ~4~
______________________________________________________________________
Classical probability
It is based on the fact that all outcomes in a sample space are equally likely to
occur all elementary events have the same probability
The probability of an event E is the division of the number of outcomes in the
sample space that satisfy this event by the total number of outcomes in the sample
space (classical definition or Laplaces Law):
() = =
The relative frequency probability is the limit of the proportion of times that event
E occurs in a large number of trials, n:
() =
The probability is the limit as n becomes large (that is, approaches infinity).
Subjective probability
The probability is determined by the degree of belief about the chance that an
event will occur.
Axiom 2. P() = 1.
______________________________________________________________________
Degree in Economics / Estefana Mourelle Espasandn 2016/2017
Lesson 2. Probability. Introduction to Probability Calculus Statistics I ~5~
______________________________________________________________________
P Ei PEi
i 1 i 1
i j ), therefore
n n
P
Ei
P E i
i 1 i 1
P(E1) P(E)
P(E) 1
, of another, E, is
6. The probability of the complementary event, E
) = 1 - P(E)
P(E
______________________________________________________________________
Degree in Economics / Estefana Mourelle Espasandn 2016/2017
Lesson 2. Probability. Introduction to Probability Calculus Statistics I ~6~
______________________________________________________________________
Conditional probability
Being aware that certain event takes place can modify the probability of obtaining the
event of interest, as there exists more information. For example: which is the probability
of getting the value 2 when we throw the dice?; how much is this probability if we
previously know that an even number has been obtained?. Both situations are different
regarding uncertainty.
Definition
The probability of event E1 conditional to event E or, in other words, the probability
that E1 occurs, given that E has taken place, is defined as
P E1 E
P E1 E , provided that P(E) > 0
P E
Also,
P E E1
P E E1 , provided that P(E1) > 0
P E1
n 1
Given the set of events Ei i 1 so that P E 0 ; then, it is verified
n
i
i 1
n
E1 E2 P En Ei
n 1
P Ei P E1 P E2 E1 P E3
i 1 i 1
______________________________________________________________________
Degree in Economics / Estefana Mourelle Espasandn 2016/2017
Lesson 2. Probability. Introduction to Probability Calculus Statistics I ~7~
______________________________________________________________________
Independence of events
Definition
P A B P A P B
Events E1, ..., En are mutually (or simultaneously) statistically independent if and
only if given the subscripts j1, j2, ..., jh, so that 1 j1 < j2 < ... < jh n, it is satisfied that:
PE j1 E j 2 E jh PE j1 PE j 2 PE jh
______________________________________________________________________
Degree in Economics / Estefana Mourelle Espasandn 2016/2017
Lesson 2. Probability. Introduction to Probability Calculus Statistics I ~8~
______________________________________________________________________
Given an event A, which can appear under the mutually exclusive alternatives
E1, E2, ..., En (A Ei ), so that
1. P(Ei) > 0, i = 1, , n.
n
2. P Ei 1 .
i 1
PE P A E .
n
Then, P A i
i 1 i
E1 E2 E3 En
BAYES THEOREM
Given an event A, which can appear under the mutually exclusive alternatives
n
E1, E2, ..., En (A Ei ), so that P(Ei) > 0 ( i = 1, , n) and P Ei 1 , and
i 1
probabilities P A
are known. It is verified that
E i
P Ei P A
P i n
E Ei
A
P Ei P A
i 1 Ei
______________________________________________________________________
Degree in Economics / Estefana Mourelle Espasandn 2016/2017