Analysis of Economic

Data
Topic 3
Probability
Chapter 3
Probability consists of and , where is a sample
space, and is a function which takes an event as
inputs and returns as output.
• Axioms of Probability
o
o
o Let denote the basic outcomes. Then

 where the notation implies that the summation

extends over all the basic outcomes in
 Probability Properties
Some consequences of axioms of probability
1. If the sample space, , consists of equally likely basic outcomes, ,
then

2. If the sample space, , consists of equally likely basic outcomes and

event consists of of these outcomes, then

3. If and are mutually exclusive events. Then

o In general, if are mutually exclusive events, then

4. If are collectively exhaustive events, the probability of their union
is
o
• The total number of permutations of objects
chosen from
o The number of possible arrangements when objects are
to be selected from a total of without replacement and
arranged in order

Order matters Order doesn’t matter

W/
replacement
W/o
replacement
• The number of combinations of objects chosen
from :
o The number of possible arrangements when objects
are to be selected from a total of without
replacement and unordered
How many ways we can
create a -element subset
from a set with elements

Order matters Order doesn’t matter

W/
replacement
W/o
replacement
 Conditional Probability
• The conditional probability of event given
that event has occurred is

o Intuitions
The multiplication
• Theorems rule
o
o
Bayes’ theorem

Conditionalizing on

o where is a partition of
Analysis of Economic
Data
Topic 4
Discrete Random Variables
Chapter 4
The binomial random variable is the number of
successes in independent trials of a random variable,
denoted as
• Its PMF for the binomial random variable is as follows:
Binomial coefficient:
Number of sequences

– The event “ successes resulting from independent trials”

can occur mutually exclusively ways, each with probability

o Mean:
o Variance:
 • A random sample of objects is
chosen from a group of objects,
of which are “successes”.

𝑁−𝐾
• The distribution of the number of
“successes” in the sample, ,
follows the hypergeometric
distribution, denoted as
Choose objective from the Choose the rest objectives from
“success” group the “failure” group

(
( objectives)
𝑃 ( 𝑥 )=
𝐾
𝑥 )( 𝑁 −𝐾
𝑛− 𝑥 )
( objectives)

(𝑛)
𝑁

where is any integer value such that

 Poisson Distribution
The random variable is said to follow the Poisson distribution, ,
if it has PMF

– The mean and variance are:

where
o : the probability of successes over a given time or space, given
o : the rate parameter, the expected number of successes per time or space
unit,
o the mathematical constant approximated by 2.71828. It is the base for
natural logarithms, called Euler’s number
Analysis of Economic
Data
Topic 5
Continuous Random Variables
Chapter 5
 Discrete RV Continuous RV

CDF CDF

Relation between PDF and CDF

Relation between PMF and CDF
and differentiable

a step function
not differentiable
 Discrete RV Continuous RV

Expectation Expectation

𝑉𝑎𝑟 ( 𝑋 )=𝐸 [ ( 𝑋 −𝜇 𝑋 ) ]= 𝐸 [ 𝑋 ] − 𝐸 [ 𝑋 ]
2 2 2

Variance Variance

Let be some function of Let be some function of

In general , 𝐸 [ 𝑔 ( 𝑋 ) ] ≠ 𝑔(𝐸 [ 𝑋 ]) unless g(𝑥) is linear

LOTUS: law of the
unconscious statistician
 Expectation
• The expected value (expectation, or mean), , of a continuous
random variable is defined as

– The probability of any specific value is zero for a continuous random

variable, the expected values for continuous random variables are
computed using integral calculus.
– It is defined through an approximation of a discrete random variable
• The variance of is defined as the expectation of the squared
deviation, , of the random variable from its mean

or

• The standard deviation of , , is the positive square root of the

variance
A RV follows a normal distribution (also known as Gaussian distribution)
with parameters and , denoted as , then for
• The PDF
A normal distribution is
• The CDF determined completely
by its mean and
variance
• The mean and variance

where
 and are any numbers such that and
 the mathematical constant approximated by 2.71828. It is the base for
natural logarithms, called Euler’s number
 the mathematical constant approximated by 3.14159, Archimedes’
constant
 quantile

−𝑧 𝛼 𝑧𝛼

The area of lower tail The area of upper tail

Knowing 

Knowing 
Any normally distributed random variable

• If is any interval of such that , then

Analysis of Economic
Data
Topic 6
Joint Distribution
Chapter 4 & 5
 Discrete RV Continuous RV

Joint CDF

Joint PMF Joint PDF

see appendix

Getting marginal prob Getting marginal prob

∑ ∑ 𝑃 ( 𝑥 , 𝑦 )=1 ∞

∫∫
∞
𝑓 𝑋 ,𝑌 ( 𝑥 , 𝑦 ) 𝑑𝑥 𝑑𝑦= 1
𝑥 𝑦 −∞ −∞
 Discrete RV Continuous RV

𝐶𝑜𝑣 ( 𝑋 , 𝑌 )= 𝐸 [ ( 𝑋 − 𝜇 𝑋 ) ( 𝑌 −𝜇 𝑌 ) ] = 𝐸 [ 𝑋𝑌 ] − 𝜇 𝑋 𝜇𝑌
𝐶𝑜𝑣 ( 𝑋 , 𝑌 )
𝜌 =𝐶𝑜𝑟𝑟 ( 𝑋 , 𝑌 ) =
𝜎 𝑋 𝜎𝑌

𝐶𝑜𝑣 ( 𝑋,𝑌 )=∑∑ (𝑥−𝜇𝑋)(𝑦−𝜇𝑌)𝑃 (𝑥 , 𝑦)=∑∑ 𝑥𝑦𝑃(𝑥, 𝑦)−𝜇𝑋𝜇𝑌

∞∞
𝐶𝑜𝑣 ( 𝑋,𝑌 )=∫ ∫ 𝑥𝑦 𝑓 𝑋,𝑌 (𝑥 ,𝑦 ) 𝑑𝑥𝑑𝑦−𝜇𝑋 𝜇𝑌
𝑥𝑦 𝑥𝑦 −∞ −∞
Let be a real-valued function of and

joint PMF joint PDF

2D LOTUS
 Discrete RV Continuous RV

Conditional PMF Conditional PDF

Conditional mean Conditional mean

Conditional variance Conditional variance

 Discrete RV Continuous RV

RVS are independent if and only if

joint CDF

RVS are independent: RVS are independent:

if and only if if and only if
joint PMF joint PDF

Must hold for all values of Must hold for all values of and

𝑃 ( 𝑥|𝑦 )= 𝑃 ( 𝑥) ↔𝑖𝑛𝑑𝑒𝑝𝑒𝑛𝑑𝑒𝑛𝑐𝑒 𝑓 𝑋∨𝑦 ( 𝑥|𝑦 )= 𝑓 𝑋 ( 𝑥) ↔𝑖𝑛𝑑𝑒𝑝𝑒𝑛𝑑𝑒𝑛𝑐𝑒

If and independent
 Joint Distribution
• Let and be a pair of random variables (discrete or
random) with mean and and variances and

– For any constant and , has

• Let be random variables (discrete or random)

with mean and variances

– For any constant , has