Econometrics-I-24

# Econometrics-I-24 - Econometrics I Professor William Greene...

This preview shows pages 1–10. Sign up to view the full content.

Part 24: Bayesian Estimation Econometrics I Professor William Greene Stern School of Business Department of Economics

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Part 24: Bayesian Estimation Econometrics I Part 24 – Bayesian Estimation ™    1/34
Part 24: Bayesian Estimation Bayesian Estimators p “Random Parameters” vs. Randomly Distributed Parameters p Models of Individual Heterogeneity n Random Effects: Consumer Brand Choice n Fixed Effects: Hospital Costs ™    2/34

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Part 24: Bayesian Estimation Bayesian Estimation p Specification of conditional likelihood: f(data | parameters) p Specification of priors: g(parameters) p Posterior density of parameters: p Posterior mean = E[parameters|data] ™    3/34 (data | parameters) (parameters) (parameters|data) (data) f g f f =
Part 24: Bayesian Estimation The Marginal Density for the Data is Irrelevant ™    4/34 f(data| )p( ) L(data| )p( ) f( | data) f(data) f(data) Joint density of   and data is f(data, ) = L(data| )p( ) Marginal density of the data is           f(data)= f(data, )d L(data| )p( )d Thus,  f( | data β β β β β β β = = β β β β β β = β β β β L(data| )p( ) ) L(data| )p( )d  L(data| )p( )d Posterior Mean =   p( | data)d  L(data| )p( )d Requires specification of the likeihood and the prior. β β β β β β = β β β β β β β β β = β β β

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Part 24: Bayesian Estimation Computing Bayesian Estimators p First generation: Do the integration (math) p Contemporary - Simulation: n (1) Deduce the posterior n (2) Draw random samples of draws from the posterior and compute the sample means and variances of the samples. (Relies on the law of large numbers.) ™    5/34 (data | ) ( ) ( | data) (data) f g E d f β β β = β β
Part 24: Bayesian Estimation Modeling Issues p As N , the likelihood dominates and the prior disappears  Bayesian and Classical MLE converge. (Needs the mode of the posterior to converge to the mean.) p Priors n Diffuse  large variances imply little prior information. (NONINFORMATIVE) n INFORMATIVE priors – finite variances that appear in the posterior. “Taints” any final results. ™    6/34

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Part 24: Bayesian Estimation A Practical Problem ™    7/34 + + - σ - - - - - σ μ π σ Γ + σ × - - σ - 2 2 v 1 2 v 2 2 vs (1/ ) K / 2 2 1 1/ 2 2 2 1 1 Sampling from the joint posterior may be impossible. E.g., linear regression. [vs ] 1 f( , | , ) e [2 ] | ( ) | (v 2) exp( (1/ 2)( ) [ ( ) ] ( )) What is this??? T y X X X β b X X b β β σ 2 o do 'simulation based estimation' here, we need joint observations on ( , ). β
Part 24: Bayesian Estimation A Solution to the Sampling Problem ™    8/34 σ σ 2 2 The joint posterior, p( , |data) is intractable.  But, For inference about  , a sample from the marginal      posterior, p( |data) would suffice.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern