Download presentation

Presentation is loading. Please wait.

Published byBrayan Oxendine Modified over 4 years ago

1
Estimation of Production Functions: Random Effects in Panel Data Lecture IX

2
Fall 2005Lecture IX2 Basic Setup Regression analysis typically assumes that a large number of factors affect the value of the dependent variable, while some of the variables are measured directly in the model the remaining variables can be summarized by a random distribution

3
Fall 2005Lecture IX3 When numerous observations on individuals are observed over time, it is assumed that some of the omitted variables represent factors peculiar to individual and time periods. Going back to the panel specification

4
Fall 2005Lecture IX4

5
Fall 2005Lecture IX5

6
Fall 2005Lecture IX6 The variance of y it on x it based on the assumption above is Thus, this kind of model is typically referred to as a variance-component (or error-components) model.

7
Fall 2005Lecture IX7 Letting the panel estimation model can be written in vector form as

8
Fall 2005Lecture IX8 The expected value of the residual becomes

9
Fall 2005Lecture IX9 Using the basic covariance estimator Whether α i is fixed or random the covariance estimator is unbiased. However, if the α i is random the covariance estimator is not the best linear unbiased estimator (BLUE). Instead, a BLUE estimator can be derived using generalized least squares (GLS).

10
Fall 2005Lecture IX10 The Generalized-Least-Squares Estimator Because both u it and u is contain α i, they are correlated.

11
Fall 2005Lecture IX11

12
Fall 2005Lecture IX12 A procedure for estimation

13
Fall 2005Lecture IX13

14
Fall 2005Lecture IX14 This looks bad, but think about

15
Fall 2005Lecture IX15

16
Fall 2005Lecture IX16 Solving this system yields

17
Fall 2005Lecture IX17 Using the inverse of a partitioned matrix

18
Fall 2005Lecture IX18 Where Where β b is the between estimator.

19
Fall 2005Lecture IX19 The variance of the estimator can be written as

20
Fall 2005Lecture IX20 3.Given that we dont know ψ a priori, we estimate

Similar presentations

OK

University of Colorado Boulder ASEN 5070 Statistical Orbit determination I Fall 2012 Professor George H. Born Professor Jeffrey S. Parker Lecture 11: Batch.

University of Colorado Boulder ASEN 5070 Statistical Orbit determination I Fall 2012 Professor George H. Born Professor Jeffrey S. Parker Lecture 11: Batch.

© 2018 SlidePlayer.com Inc.

All rights reserved.

To make this website work, we log user data and share it with processors. To use this website, you must agree to our Privacy Policy, including cookie policy.

Ads by Google