Fundamentals of Probability

Introduction to Econometrics
ECON 115
What is Econometrics?
• Application of Statistical Methods in Economics
• Regression Analysis – tries to elicit relationships of variables to a dependent

variable. Looking for expected values of a corresponding variable.
• We allow Y or the dependent variable to be explained by several Xs or

independent variable through some functional form.
• In mathematical notation:
Y = f(X1, X2, X3, …, Xk)
What is Econometrics?
• We want to know how large the effect of the independent variables to
the dependent variable; also to which direction is the relationship
heading.
• We use econometrics to:

a. test economic theory and hypothesis,
b. forecasting economic variables, and
c . evaluating the effect or impact of government or business policy.
Possible uses for Econometrics
• A city council ponders the question of how much violent crime will be
reduced if an additional million dollars is spent putting uniformed police on
the street.
• The CEO of Proctor & Gamble must estimate how much demand there will be
in ten years for the detergent Tide, and how much to invest in new plant and
equipment.
• You must decide how much of your savings will go into a stock fund, and how
much into the money market. This requires you to make predictions of the
level of economic activity, the rate of inflation, and interest rates over your
planning horizon.
An example from Labor Economics
Wage = f(education, experience)
• This model of explaining wage can estimate RETURNS TO

EDUCATION; it is how much more wage can an additional year of
education give.
• Instead of having to explain wage with continuous explanatory

variables, we can also try to cite specific types of education (high
school, college, MS, PhD graduate) and experience (having worked as
an analyst for a reputable institution).
Three types of economic data
1. Cross-sectional - observations across entities for a specific time
period. Usually gathered through surveys.
2. Time series - observations over time for a specific entity. Usually

gathered through annual reports and government statistics.
3. Panel/Longitudinal – observations over time and entities

Econometrics vs Hard Science
• Essentially data in economics is observational. That is we
observe the decisions, behaviors and characteristics of
individuals, firms, governments and countries.
• Contrary to what is called as experimental data these
observations are not or cannot be controlled.
• We cannot perfectly account for the individual effects of
each independent variable to the dependent variable
because we are dealing with people and their interactions.
Simple Linear Regression
Wage
Residual
E(Wage|Experience) =
β0 + β1Experience
Experience
Regression Analysis
• Simple Linear Regression Model
Wage = β0 + β1 Experience + u
Slope = β0 and intercept = β1
• Multiple Linear Regression Model

Wage = β0 + β1 Experience + β2 Education + … + βk Xk + u
Review of Probability Fundamentals
Random Variable
• Benjamin Franklin once said that the only two things that are certain
in life are death and taxes.
• Almost all things that we encounter in life are uncertain.
• Probability provides a way for us to convey possible outcomes pf an
event.
• Example: what is the probability that a plane will be booked fully?
Random Variable (cont’d)
• A random variable is a variable whose value is unknown until it is
observed; in other words it is a variable that is not perfectly
predictable.
• Discrete random variable – takes in values that are countable
- indicator variables
• Continuous random variable – can take in any value in an interval
• The number of passengers that will board a plane is a random

variable.
Probability Distributions
Random experiment
- random selection
- defines probabilities
Random variable
- a rule for assigning numerical values to experimental outcomes
Probability Distributions (cont’d)
• An experiment: Out of 10 slips of paper,
• let X be a discrete random variable that contains the number on a slip
drawn randomly where X can have values x = 1, 2, 3, or 4
• let Y be a discrete random variable which assigns 1 to slips that are
shaded, and 0 if the slip is not shaded
Probability Density Function (pdf)
• After many draws we can create a probability distribution for each
variable through the frequency of each outcome being drawn.
Probability Distributions (cont’d)
• For a discrete random variable X the value of the probability density
function f(x) is the probability that the random variable X takes the
value x, f(x) = P(X = x).
• Because f(x) is a probability, it must be true that 0 < f(x) < 1 and, if X
takes n possible values x1, . . . , xn, then the sum of their probabilities
must be one.
Cumulative Density Function (cdf)
• Gives the probability that X is less than or equal to a specified value
for x.
F(x) = P( X ≤ x )
• From the table from 2 slides above, gives us:

F(1) = f(x=1) = 0.1
F(2) = f(x=1) + f(x=2) = 0.1 + 0.2 = 0.3
F(3) = f(x=1) + f(x=2) + f(x=3) = 0.1 + 0.2 + 0.3 = 0.6
F(4) = f(x=1) + f(x=2) + f(x=3)+ f(x=4) = 0.1 + 0.2 + 0.3 +0.6 = 1
Getting probabilities from pdfs
• If we ask the probability of X when it is greater than 2 –
P(X > 2) = 1 – P (X ≤ 2) = 1 – F(2) = 1 – 0.3 = 0.7
• Question : What is the probability that we observe X = 2.5?

Probability Distribution of Continuous
Variables
Joint Probability Density Function
• Shows the probability of two events happening at the same time.
• With our example, the joint probability that the drawn slip is shaded
and has a number is 0.10.
Marginal Distributions
• We can show the probability that the drawn slip is shaded by adding
the probability for each shaded x. Therefore, for our example, the
probability of drawing a shaded slip is 0.4.
Conditional Probability
• What is the probability that a drawn slip will get a value of 2 given
that it is shaded?
• Four slips are shaded, one of them is a 2. Therefore, the conditional
probability for observing that event is 0.25.
• With conditional probability, a new population is observed from the
set conditioning.
Statistical Independence
• Two random variables are statistically independent if the conditional
probability that X = x given that Y = y, is the same as the unconditional
probability that X = x for all pairings in a discrete probability
distribution.
• If it turns out that the probabilities do not match for at least one of
any pairing of the values of x and y, then X and Y are statistically
dependent.
• For our example: the conditional probability that a shaded slip is

numbered 2 is 0.25. the marginal probability of a drawing a slip that is
numbered 2 is 0.2. Thus X and Y are statistically dependent.
Statistical Independence
• Statistical dependence gives us the

Fundamentals of Probability

Uploaded by

Copyright:

Available Formats

Fundamentals of Probability

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Fundamentals of Probability

Uploaded by

Copyright:

Available Formats

Introduction to Econometrics

• Regression Analysis – tries to elicit relationships of variables to a dependent

• We allow Y or the dependent variable to be explained by several Xs or

• We use econometrics to:

• This model of explaining wage can estimate RETURNS TO

• Instead of having to explain wage with continuous explanatory

2. Time series - observations over time for a specific entity. Usually

3. Panel/Longitudinal – observations over time and entities

• Multiple Linear Regression Model

• The number of passengers that will board a plane is a random

• From the table from 2 slides above, gives us:

• Question : What is the probability that we observe X = 2.5?

• For our example: the conditional probability that a shaded slip is

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.