Econometrics I

Professor William Greene

Stern School of Business
Department of Economics

1-1/22 Part 1: Introduction

 Econometrics I

Part 1 - Paradigm

1-2/22 Part 1: Introduction

 Econometrics: Paradigm
 Theoretical foundations
 Microeconometrics and
macroeconometrics
 Behavioral modeling: Optimization, labor
supply, demand equations, etc.
 Statistical foundations
 Mathematical Elements
 ‘Model’ building – the econometric
model
 Mathematical elements
 The underlying truth – is there one?

1-3/22 Part 1: Introduction

 Why Use This Framework?
 Understanding covariation
 Understanding the relationship:
 Estimation of quantities of interest such as
elasticities
 Prediction of the outcome of interest
 The search for “causal” effects
 Controlling future outcomes using
knowledge of relationships

1-4/22 Part 1: Introduction

 Model Building in Econometrics

 Role of the assumptions

 Parameterizing the model
 Nonparametric analysis
 Semiparametric analysis
 Parametric analysis
 Sharpness of inferences

1-5/22 Part 1: Introduction

 Application: Is there a relationship between investment
and capital stock? (10 firms, 20 years)

1-6/22 Part 1: Introduction

 Nonparametric Regression

Kernel Regression
Ni=1 w i (z)y i
F̂(z)= N
i=1 w i (z)
1  x i -z 
w i (z)  K
   
  .9s / N0.2
K(t)  (t)[1  (t)]
exp(t)
(t) 
1  exp(t)

What are the assumptions? What are the conclusions?

1-7/22 Part 1: Introduction

 Semiparametric Regression
 Investmenti,t = a + b*Capitali,t + ui,t
 Median[ui,t | Capitali,t] = 0

Least Absolute Deviations

ˆ ˆ ˆ
F(x)=a+bx
ˆ 
N
â,b=ArgMina,b i1
|y i  a-bx i |

1-8/22 Part 1: Introduction

 Fully Parametric Regression
 Investmenti,t = a + b*Capitali,t + ui,t
 ui,t | Capitalj,s ~ N[0,2] for all i,j,s,t
 Ii,t|Ci,t ~ N[a+bCit,2]

Least Squares Regression

ˆ ˆ ˆ
F(x)=a+bx

a,b  i1 (y i  a  bx i )
ˆ ˆ
a,b=ArgMin
N 2

1
   
N  1  1  N 1 
=   i=1        i=1  y i 
  xi   xi     xi  
 

1-9/22 Part 1: Introduction

 Estimation Platforms
 The “best use” of a body of data
 Sample data
 Nonsample information
 The accretion of knowledge
 Model based
 Kernels and smoothing methods (nonparametric)
 Moments and quantiles (semiparametric)
 Likelihood and M- estimators (parametric)
 Methodology based (?)
 Classical – parametric and semiparametric
 Bayesian – strongly parametric

1-10/22 Part 1: Introduction

 Classical Inference

Population Measurement

Econometrics
Characteristics
Imprecise inference about Behavior Patterns
the entire population –
sampling theory and Choices
asymptotics

1-11/22 Part 1: Introduction

 Bayesian Inference

Population Measurement

Econometrics
Characteristics
Sharp, ‘exact’ inference about Behavior Patterns
only the sample – the ‘posterior’
density. Choices

1-12/22 Part 1: Introduction

 Data Structures

 Observation mechanisms
 Passive, nonexperimental
 Active, experimental
 The ‘natural experiment’
 Data types
 Cross section
 Pure time series
 Panel – longitudinal data
 Financial data

1-13/22 Part 1: Introduction

 Estimation Methods and Applications
 Least squares etc. – OLS, GLS, LAD, quantile
 Maximum likelihood
 Formal ML
 Maximum simulated likelihood
 Robust and M- estimation
 Instrumental variables and GMM
 Bayesian estimation – Markov Chain Monte Carlo methods

1-14/22 Part 1: Introduction

 Trends in Econometrics
 Small structural models vs. large scale multiple
equation models
 Non- and semiparametric methods vs. parametric
 Robust methods – GMM (paradigm shift)
 Unit roots, cointegration and macroeconometrics
 Nonlinear modeling and the role of software
 Behavioral and structural modeling vs. “reduced
form,” “covariance analysis”
 Pervasiveness of an econometrics paradigm
 Identification and “Causal” effects

1-15/22 Part 1: Introduction

 Course Objective
Develop the tools needed to read
about with understanding and to do
empirical research using the current
body of techniques.

1-16/22 Part 1: Introduction

 Prerequisites
 A previous course that used regression
 Mathematical statistics
 Matrix algebra

We will do some proofs and derivations

We will also examine empirical applications

1-17/22 Part 1: Introduction

 Readings

 Main text: Greene, W., Econometric

Analysis, 7th Edition, Prentice Hall, 2012.
 A few articles
 Notes and materials on the course
website:
http://people.stern.nyu.edu/wgreene/Econometrics/Econometrics.htm

1-18/22 Part 1: Introduction

 http://people.stern.nyu.edu/wgreene/Econometrics/Econometrics.htm

1-19/22 Part 1: Introduction

 The Course Outline

No class on:
Thursday, September 5

Midterm: October 22

1-20/22 Part 1: Introduction

 Course Applications

 Software
 LIMDEP/NLOGIT provided, supported
 SAS, Stata, EViews optional, your choice
 R, Matlab, Gauss, others
 Questions and review as requested
 Problem Sets: (more details later)

1-21/22 Part 1: Introduction

 Course Requirements

 Problem sets: 5 (25%)

 Midterm, in class (30%)
 Final exam, take home (45%)
 Enthusiasm

1-22/22 Part 1: Introduction