Business Research Methods

Lecture 4-5

by Selim Bora
The Idea of Probability
 Chance behavior is unpredictable in the short run but has a regular
and predictable pattern in the long run.

 We call a phenomenon random if individual outcomes are uncertain

but there is nonetheless a regular distribution of outcomes in a large
number of repetitions.

 The probability of any outcome of a random phenomenon is a

number between 0(the outcome never occurs) and 1(always occurs)
that describes the proportion of times the outcome would occur in a
very long series of repetitions.

 Probabilities describe only what happens in the long run, short runs
of random phenomena often don’t look random to us because they
do not show the regularity that in fact emerges only in very many
repetitions.
Personal Probabilities
A personal probability of an outcome is a number
between 0 and 1 that expresses an individual’s
judgment of how likely the outcome is.

Different people can have different personal

probabilities, and a personal probability need not agree
with a proportion based on data about similar cases.
Probability Models
A probability model for a random phenomenon
describes all the possible outcomes and says how to
assign probabilities to any collection of outcomes. We
sometimes call a collection of outcomes an event.

There are two simple ways to give a probability model.

The first assigns a probability to each individual
outcome. These probabilities must be numbers between
0 and 1, and they must add to exactly 1.

The second kind of probability model assigns

probabilities as areas under a density curve.
Probability Rules
 Any probability is a number between 0 and 1.

 All possible outcomes together must have probability 1.

 The probability that an event does not occur is 1 minus the

probability that the event does not occur.

 If two events have no outcomes in common, the probability

that one or the other occurs is the sum of their individual
probabilities.

 Any assignment of probabilities to all individual outcomes

that satisfies first two rules is legitimate.
Sampling Distribution
The sampling distribution of a statistic tells us what
values the statistic takes in repeated samples from the
same population and how often it takes those values.

We think of a sampling distribution as assigning

probabilities to the values the statistic can take. Because
there are usually many possible values, sampling
distributions are often described by a density curve.

The total probability is 1 because the total area under the

curve is 1.
Simulation
Using random digits from a table or from computer software to
imitate chance behavior is called simulation.

We can use random digits to simulate random outcomes if we

know the probabilities of the outcomes in three stages:
Give probability model
Assign digits to represent outcomes
Simulate many repetitions

Two random phenomena are independent if knowing the

outcome of one does not change the probabilities for outcomes
of the other.
More Elaborate Simulations
Other simulations may require varying number of
trials or different probabilities at each stage or may
have stages that are not independent so that the
probabilities at some stage depend on the outcome of
earlier stages.

A tree diagram can be helpful by giving the

probability model in graphical form.
Expected Values
When the outcomes are numbers, as in games of chance,
we are also interested in the long-run average outcome.

The expected value of a random phenomenon that has

numerical outcomes is found by multiplying each
outcome by its probability and then adding all the
products.

In symbols, if the possible outcomes are a1, a2, …, ak and

their probabilities are p1, p2, …, pk, the expected value is

expected value = a1p1 + a2p2 + … + akpk

The Law of Large Numbers
According to the law of large numbers, if a random
phenomenon with numerical outcomes is repeated
many times independently, the mean of the actually
observed outcomes approaches the expected value.

If you don’t know the outcome probabilities, you can

estimate the expected value(along with probabilities)
by simulation.