Instrumental Variables Regression
(SW Ch. 10)
Three important threats to internal validity are:
omitted variable bias from a variable that is correlated with X but is unobserved, so cannot be included in the
regression;
simultaneous causality bias (X caus
- GiveWin 2.02 session started at 16:54:43 on Wednesday 17 October 2001 -nic3.in7 loaded from C:\Winword\Econometrics\PcGive exercises\nic3.in7 Algebra code for nic3.in7: DLG = diff(LG,1); DLWTI = diff(LWTI,1); nic3.in7 saved to C:\Winword\Econometrics\Pc
File: C:\Winword\Econmet\Ref2.DOC SOME THEORETICAL WORK ON THE CONSUMPTION FUNCTION Davidson, Hendry, Srba and Yeo [DHSY] (EJ 1978) consider the steady state theory:
C = KY
(1)
Taking logs of (1) and imposing the parameter restriction =1 yields ln C = ln
File: C:\WINWORD\MSCBE\Ref1.DOC
UNIVERSITY OF STRATHCLYDE
QM&FT LECTURE NOTES
ESTIMATION AND STATISTICAL INFERENCE
VARIETY OF DIFFERENT ASSUMPTIONS
UNDER
A
Aims
In these notes, we examine the properties of parameter estimators and of several regressionbas
File: C:\WINWORD\ECONMET\Reading.DOC
UNIVERSITY OF STRATHCLYDE
APPLIED ECONOMETRICS LECTURE NOTES
APPLIED ECONOMETRICS READING LIST
General references and recommended reading.
(A) Useful articles or books on specific topics:
Davidson, J.E.H., D.F. Hendry,
Regression with Panel Data
(SW Ch. 8)
A panel dataset contains observations on multiple entities (individuals), where each entity is observed at two or more points in
time.
Examples:
Data on 420 California school districts in 1999 and again in 2000, for 8
EQ( 5) Modelling DLCE by OLS (using nic4.in7)
The present sample is: 1970 (1) to 1990 (4) less 8 forecasts
The forecast period is: 1989 (1) to 1990 (4)
Variable
DLY
Constant
DDLY_1
DLNW_1
LY_1
LNW_1
LCE_1
DUM
Coefficient
0.28055
0.068577
0.15319
0.14131
0
File: C:\WINWORD\ECONMET\Lecture4.DOC
UNIVERSITY OF STRATHCLYDE
ECONOMETRICS LECTURE NOTES
STOCHASTIC REGRESSORS, INSTRUMENTAL VARIABLES AND
WEAK EXOGENEITY
1. INTRODUCTION
In certain circumstances, the OLS estimator is optimal; it is the best estimator t
File: C:\WINWORD\ECONMET\Lecture2 full version.DOC UNIVERSITY OF STRATHCLYDE APPLIED ECONOMETRICS LECTURE NOTES MODEL MIS-SPECIFICATION AND MIS-SPECIFICATION TESTING Aims The estimates derived from linear regression techniques, and inferences based on tho
File: Lecture2.DOC
MODEL MIS-SPECIFICATION AND MIS-SPECIFICATION
TESTING
We have four main objectives.
(1) To examine what is meant by the misspecification of an
econometric model.
(2) To identify the consequences of estimating a misspecified
econometric
Lecture1 presentation small ECONOMETRIC MODELLING: THE 'GENERAL TO SPECIFIC' PROCEDURE. (A) Some "facts of life": Economic theory does not tell us much about form & content of empirical model Dynamics matter: adjustments are not instantaneous Want to incl
Lecture1 presentation ECONOMETRIC MODELLING: THE 'GENERAL TO SPECIFIC' PROCEDURE. (A) Some "facts of life": Economic theory does not tell us much about form & content of empirical model Dynamics matter: adjustments are not instantaneous Want to include "r
File: C:\WINWORD\ECONMET\Lecture1.DOC
UNIVERSITY OF STRATHCLYDE
APPLIED ECONOMETRICS LECTURE NOTES
ECONOMETRIC MODELLING: THE HENDRY APPROACH, AND THE 'GENERAL TO
SPECIFIC' PROCEDURE.
(A) SETTING THE SCENE: THE PROBLEM
ECONOMIC THEORY
Suppose that economi
Applied Econometrics Lab 3 The aim of this exercise is to replicate the results of Stock and Watson, Chapter 8. This exercise uses the Panel Data set: fatality.xls The data are for the "lower 48" U.S. states (excluding Alaska and Hawaii), annually for 198
File: WINWORD\ECONMET\PcGive exercises\LAB3.DOC
APPLIED ECONOMETRICS: COMPUTER SESSION 3
INSTRUMENTAL VARIABLES ESTIMATION
1. For this exercise, you will need to load your latest saved version of the GiveWin/PcGive file (probably
called Nic3.in7 or someth
File: WINWORD\ECONMET\PcGive exercises\Lab2.doc
APPLIED ECONOMETRICS: COMPUTER SESSION 2
To complete this exercise, you will need the GiveWin file saved from the previous exercise (that should have
the filename Nic2.in7).
OBJECTIVE
We estimate a parsimoni
IV Estimation
Instrumental Variables
Yt = 1 + 2 X2,t +.+ k Xk,t + u t t = 1,.,T
Y = X + u
Y = X + u
-1 ^ OLS = (XX ) XY
-1 / / ^ OLS = (X X ) X (X + u ) -1 / -1 / / / ^ OLS = (X X ) X X + (X X ) X u )
-1 ^ OLS = + (XX ) Xu
^ If Cor (X, u ) 0, then E ( OLS
File: C:\WINWORD\ECONMET\HYPTEST.DOC HYPOTHESIS TESTING IN THE GENERAL LINEAR MODEL The general linear model can be represented in various ways:
Yi = 1 + X2,i 2 +.+ Xk,i k + ui i = 1,., n
or in terms of all n observations on each variable written explicit
File: Hints on lab exercise 1 OBTAINING A PARSIMONIOUS MODEL: GENERAL-TO-SPECIFIC SEARCHING Load and save updated GiveWin file (perhaps saved under name NIC2, which includes all data transformations). Do following steps: 1. Select Modules, Start PcGive, M
Applied Econometrics (Answer to Reparameteristion.doc) Mini exercise Q1: Demonstrate that each of the following is a reparameterisation of the other, and identify the relationships between the and parameters:
Yt = 1 + 2 X t + 3X t -1 + 4 Yt -1 Yt = 1 + 2
31 456 Applied Econometrics
Assessment Exercise 1 2005/2006
This assessment exercise is based on the computer laboratory exercises 1, 2 and 3.
That is, it covers dynamic regression model estimation techniques and the generalto-specific modelling strategy;
31 456 Applied Econometrics Second Assessment Exercise 2004/2005 The assessment exercise covers the material discussed in the entire course, but focuses particularly on the topics that deal with unit roots and cointegration. The data set is contained in a