Forecast Many Predictors I Slides

Forecast Many Predictors I Slides - NBER Summer Institute...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
Revised July 23, 2008 11-1 NBER Summer Institute What’s New in Econometrics – Time Series Lecture 11 July 16, 2008 Forecasting and Macro Modeling with Many Predictors, Part I
Background image of page 1

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

View Full DocumentRight Arrow Icon
Revised July 23, 2008 11-2 Outline Lecture 11 1) Why Might You Want To Use Hundreds of Series? 2) Dimensionality: From Curse to Blessing 3) Dynamic Factor Models: Specification and Estimation Lecture 12 4) Other High-Dimensional Forecasting Methods 5) Empirical Performance of High-Dimensional Methods 6) SVARs with Factors: FAVAR 7) Factors as Instruments 8) DSGEs and Factor Models
Background image of page 2
Revised July 23, 2008 11-3 1) Why Might You Want To Use Hundreds of Series? A theme of these lectures has been the challenge of working with limited information (problems of identification) in macro time series. But all the work until now has focused on models with relatively few variables. In fact, however, thousands of economic time series are available on line in real time. Can these be used for economic monitoring and forecasting? For estimation of single and multiple equation models? This is a radical proposal! not your “principle of parsimony”! VARs with 6 variables and 4 lags have 4 × 6 2 = 144 coefficients (plus variances)
Background image of page 3

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

View Full DocumentRight Arrow Icon
Revised July 23, 2008 11-4 Why use hundreds of series, ctd. We will consider four specific problems in which more information would be most welcome: 1.Economic monitoring (“nowcasting”) and forecasting can we move from small models with forecasts adjusted by judgmental use of additional information, to a more scientific system that incorporates as much quantitative information as possible? 2.SVARs using more information so innovations span the space of shocks 3.IV estimation more information might produce stronger instruments 4.DSGE estimation more information might produce stronger identification
Background image of page 4
Revised July 23, 2008 11-5 Why use hundreds of series, ctd. It turns out that dynamic factor models (Geweke (1977), Sargent and Sims (1977)) have proven very useful in this research program The greatest amount of experience to date with DFMs is for forecasting. DFMs are in use for real-time monitoring and forecasting (e.g. CFNAI (Federal Reserve Bank of Chicago), Giannone, Reichlin, and Small (2008), Aruoba, Diebold, and Scotti (2008) Other promising applications o SVARs: Bernanke, Boivin, and Eliasz’s (2005) FAVAR o DSGEs: Boivin and Giannoni (2006b) In a broader sense, the move of empirical macro to use much larger data sets is consistent with developments in other scientific areas – mainly experimental sciences (especially life sciences/genomics) but also some observational sciences (astrophysics).
Background image of page 5

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

View Full DocumentRight Arrow Icon
Revised July 23, 2008 11-6 Outline of the next two lectures 1) Why Might You Want To Use Hundreds of Series? 2) Dimensionality: From Curse to Blessing 3) Dynamic Factor Models: Specification and Estimation 4) Other High-Dimensional Forecasting Methods 5) Empirical Performance of High-Dimensional Methods 6) SVARs with Factors: FAVAR 7) Factors as Instruments 8) DSGEs and Factor Models
Background image of page 6
2) Dimensionality: From Curse to Blessing The curse part:
Background image of page 7

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

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 12/26/2011 for the course ECON 245a taught by Professor Staff during the Fall '08 term at UCSB.

Page1 / 59

Forecast Many Predictors I Slides - NBER Summer Institute...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online