Economics 20 - Prof. Anderson 1 Econometrics ARTSFIN is
Economics 20 - Prof. Anderson 1
Econometrics ARTSFIN is
Economics 20 - Prof. Anderson 2
Data Analysis Econometrics is
Economics 20 - Prof. Anderson 3
! It used to be that statisticians were primarily the only ones who can analyze datawhat changed?;
! The most important idea when applying statistical techniques to analyze data is to know whats going on behind the number crunching so that you (and not the computer) are in control of the analysis:
n Most people do not realize that statistical software cant tell you when to use and not to use a certain statistical technique.
Economics 20 - Prof. Anderson 4
Welcome to ARTSFIN
What is Econometrics?
Economics 20 - Prof. Anderson 5
Why study Econometrics?
! Rare in economics, business, and finance (and many other areas without labs!) to have experimental data;
! Need to use non-experimental, or observational, data to make inferences
! Important to be able to apply economic
theory to real world data
Economics 20 - Prof. Anderson 6
Why study Econometrics?
! An empirical analysis uses data to test a theory or to estimate a relationship
! A formal economic model can be tested ! Theory may be ambiguous as to the effect
of some policy change can use econometrics to evaluate the program
Economics 20 - Prof. Anderson 7
Why study Econometrics?
! It will allow you (or arm you) with a tool to understand and use BIG DATA: n Data mining, analytics, machine learning n Example:
Twitter mood predicts the stock market (2011: Bolen, Mao, & Zeng)
predictions can be significantly improved by the inclusion of specific public mood dimensions but not othersaccuracy of 86.7%
Economics 20 - Prof. Anderson 8
Why study Econometrics?
! Understand the techniques used in: n Freakonomics n Moneyball: The Art of Winning an Unfair
Game n Soccernomics n Bringing Down the House (21) n Data, A Love Story
Economics 20 - Prof. Anderson 9
Types of Data
Economics 20 - Prof. Anderson 10
Types of Data Cross Sectional
! Cross-sectional data is a random sample ! Each observation is a new individual, firm,
etc. with information at a point in time ! If the data is not a random sample, we have
a sample-selection problem
Economics 20 - Prof. Anderson 11
Types of Data Panel
! Can pool random cross sections and treat similar to a normal cross section. Will just need to account for time differences.
! Can follow the same random individual
observations over time known as panel data or longitudinal data
Economics 20 - Prof. Anderson 12
Types of Data Time Series
! Time series data has a separate observation for each time period e.g. stock prices
! Since not a random sample, different
problems to consider
! Trends and seasonality will be important
Economics 20 - Prof. Anderson 13
Causation
Economics 20 - Prof. Anderson 14
The Question of Causality
! Simply establishing a relationship (correlation) between variables is rarely sufficient;
! Want to the effect to be considered causal; ! If weve truly controlled for enough other
variables, then the estimated ceteris paribus effect can often be considered to be causal;
! Can be difficult to establish causality.
Economics 20 - Prof. Anderson 15
Example: Returns to Education
! A model of human capital investment implies getting more education should lead to higher earnings
! In the simplest case, this implies an equation like
ueducationEarnings ++= 10
Economics 20 - Prof. Anderson 16
Example: (continued)
! The estimate of 1, is the return to education, but can it be considered causal?
! While the error term, u, includes other factors affecting earnings, want to control for as much as possible
! Some things are still unobserved, which can be problematic
Economics 20 - Prof. Anderson 17
Exercise
! Provide your own research questions, taking into account the causal relationship of your questions
Economics 20 - Prof. Anderson 18
Some jargon from basic statistics
Economics 20 - Prof. Anderson 19
Population Parameter
! A parameter is a number that summarizes the population, which is the entire population youre interested in investigating. n Examples of parameters include the mean of a
population, the median of a population, or proportion of a population that falls into a certain category.
Economics 20 - Prof. Anderson 20
Sample Statistic
! Most of the time, we cant determine population parameters exactlyso we take a sample (a subset of individuals), which can give us a good estimate of the population parameter.
Economics 20 - Prof. Anderson 21
Correlation
! Often misused by analysts; ! It measures strength and direction of the linear
relationship between two quantitative variables only;
! Is a number between -1.0 (perfect negative correlation) and +1.0 (perfect positive correlation)
! Note: CORRELATION IS NOT CAUSATION!
Economics 20 - Prof. Anderson 22
Linear Regression ! After weve found a correlation and determined
that two variables have a fairly strong linear relationship, we can try to make predictions for one variable based on the value of the other variable i.e. looking at the best-fitting line.
! Looking for the best-fitting line is called linear regression.
! Many types of regression exist (e.g. simple, multivariate, logistic regression, nonlinear regression)
! If you do it right, you may be able to determine CAUSATION thru regression.
Economics 20 - Prof. Anderson 23