Professional Documents
Culture Documents
Introduction To Econometrics, 5 Edition: Review: Random Variables, Sampling, Estimation, and Inference
Introduction To Econometrics, 5 Edition: Review: Random Variables, Sampling, Estimation, and Inference
Dougherty
Introduction to Econometrics,
5th edition
Chapter heading
Review: Random Variables,
Sampling, Estimation, and
Inference
The first part of the condition may be weakened to a requirement that the estimator be
asymptotically unbiased.
2
SUFFICIENT CONDITION FOR CONSISTENCY
0.3 n X
1 50
n = 1600 4 25
probability density function
25 10
0.2 100 5
400 2.5
1600 1.25
n = 400
0.1
n = 100
0.0
0 50 100 150 X
The sample mean may be shown to be consistent by this method. The figure illustrates the
simulation shown in the previous slideshow. The true value of m is 100. The distribution of
the sample mean is shown for various sample sizes.
3
SUFFICIENT CONDITION FOR CONSISTENCY
0.3 E X n X
1 50
2
n = 1600
X2 X 4 25
probability density function
n 25 10
0.2 100 5
400 2.5
1600 1.25
n = 400
0.1
n = 100
0.0
0 50 100 150 X
The sample mean is unbiased and its variance tends to zero as n becomes large.
4
SUFFICIENT CONDITION FOR CONSISTENCY
n
Z X
n1
n
E Z
n1
2
n 2
n
Z
2
X
2
n 1 2 X
n 1 n
Consider also another estimator, Z, as defined. It is biased downwards for finite n, but
asymptotically it is unbiased and its variance tends to zero. The sufficient condition shows
that it, too, is a consistent estimator of m.
5
Copyright Christopher Dougherty 2016.
Individuals studying econometrics on their own who feel that they might benefit
from participation in a formal course should consider the London School of
Economics summer school course
EC212 Introduction to Econometrics
http://www2.lse.ac.uk/study/summerSchools/summerSchool/Home.aspx
or the University of London International Programmes distance learning course
EC2020 Elements of Econometrics
www.londoninternational.ac.uk/lse.
2016.04.15