{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

lec12

# lec12 - MIT OpenCourseWare http/ocw.mit.edu 14.384 Time...

This preview shows pages 1–3. Sign up to view the full content.

MIT OpenCourseWare http://ocw.mit.edu 14.384 Time Series Analysis Fall 2008 For information about citing these materials or our Terms of Use, visit: http://ocw.mit.edu/terms .

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

View Full Document
Introduction 1 14.384 Time Series Analysis, Fall 2007 Professor Anna Mikusheva Paul Schrimpf, scribe October 18, 2007 Lecture 12 Empirical Processes Introduction References : Hamilton ch 17, Stock HoE vol 4, Andrews HoE (more mathematical) Empirical process theory is used to study limit distributions under non-standard conditions. Applications include: 1. unit root & cointegration – e.g. y = ρy t 1 + e t , if ρ = 1, then T ( ρ ˆ - 1) ? some non-standard - distribution μ + e t t τ 2. structural breaks (testing with nuisance parameters) – e.g. y t = ( . Want to test μ + k + e t t > τ H 0 : no break k = 0. Under H 0 , τ doesn’t enter the model, but it is a nuisance parameter under the alternative. A test statistic for this hypothesis is s = max τ | t τ | where t τ is the t-statistic for testing k = 0 with the break at time τ . s will have a non-standard distribution. 3. weak instruments & weak GMM 4. Simulated GMM with non-diﬀerentiable objective function – e.g. Berry & Pakes 5. semi-parametric We will discuss 1 & 2. We will cover simulated GMM later. Functional Central Limit Theorem Let x t be a real-valued random k × 1 vector. Consider some < n valued function g t ( x t , τ ) for τ Θ, where Θ is a subset of some metric space. Let 1 ξ T ( τ ) = T X ( g t ( x t , τ ) T t =1 - Eg t ( x t , τ )) ξ T ( τ ) is a random function; it maps each τ Θ to an < n valued random variable. ξ T ( τ ) is called an empirical process. Under very general conditions, standard arguments show that ξ T ( τ ) converges pointwise, i.e. τ 2 0 Θ, ξ T ( τ 0 ) N (0 , σ ( τ 0 )). Also, standard arguments imply that on a ﬁnite collection of points,
This is the end of the preview. Sign up to access the rest of the document.
• '09
• Geurrieri
• Probability theory, Stochastic process, Continuous function, Random walk, Convergence of random variables, Continuous mapping theorem

{[ snackBarMessage ]}

### Page1 / 6

lec12 - MIT OpenCourseWare http/ocw.mit.edu 14.384 Time...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online