14.384 | Fall 2013 | Graduate

Time Series Analysis


I. Introduction: Stationary Time Series
1–3 Introduction to stationary time series 
_ARMA, limit theory for stationary time series, causal relationships, HAC_
3–4 Frequency domain analysis 
_Spectra; filters; transforms; nonparametric estimation_
5 Model selection and information 
_Consistent estimation of number of lags, discussion of non-uniformity and post-selection inferences_
II. Mutivariate Stationary Analysis
6–7 VAR 
_Definition, estimation: OLS, ML, Granger causality, impulse response functions and variance decompositions_
8 Structural VARs 
_Identification, short term restrictions, long-term restrictions_
9 VAR and DSGE models 
_World decomposition, fundamentality of shocks, do long-run restrictions identify anything_
10–11 Factor model and FAVAR 
_Motivation, principal components, choosing number of static and dynamic factors, structural FAVAR, IV regression with factors_
III. Univariate Non-Stationary Processes
12 Asymptotic theory of empirical processes
13–14 Univariate unit roots and near unit root problem 
_Unit root problem, unit root testing, confidence sets for persistence, tests for stationarity_
15 Structural breaks and non-linearity 
_Testing for breaks with known and unknown dates, multiple breaks, estimating number of breaks_
IV. Multivariate Non-Stationary
16–17 Multivariate unit roots and co-integration 
_Estimating cointegration relations, canonical form_
18 Persistent regressors (prediction regression) 
_Limit theory, Stambaugh correction, nuisance parameter problem, conservative procedures, conditional procedures_
V. GMM and related issues
19 GMM and Simulated GMM 
_GMM estimation and asymptotic theory, testing in GMM setting, simulated method of moments and time series specifics: estimation of covariance structure, initial condition problem, indirect inference_
20 Weak IV 
_What is weak IV?, alternative asymptotic theory, how to detect weak IV, procedures robust to weak IV, unsolved problems._
VI. Likelihood Methods
21 Kalman filter and its applications 
_State-Space models, time varying coefficients_
22 ML estimation of DSGE 
_Stochastic singularities problem, misspecification and quasi-ML, identification_
23 Identification and weak identification of DSGE
VII. Bayesian Methods
24 Bayesian concepts
25 Markov Chain Monte Carlo (MCMC) 
_Metropolis-Hastings, Gibbs sampler, data augmentation_
26 Estimation of DSGE models using Bayesian methods

Course Info

As Taught In
Fall 2013
Learning Resource Types
Lecture Notes
Problem Sets
Instructor Insights