Discussion of Presentations on Real-Time Data Analysis Dean Croushore Associate Professor, University of Richmond Visiting Scholar, Federal Reserve Bank of Philadelphia May 2008 Data Sets Real-Time Data Set for Macroeconomists Philadelphia Fed (Tom Stark) Need for good institutional support Club good: non-rival but excludable
Data Sets Unrestricted access: U.S.: Philadelphia Fed, St. Louis Fed, BEA OECD Bank of England (recently updated) Restricted access: EABCN Fate unclear: Canada One-time research projects: Many, most not continuously updated
Role of Research for Data Production Analysis of data revisions is not criticism of government statistical agencies! May help agencies improve data production process Revisions reflect limited resources devoted to data collection Revised data usually superior to unrevised data (U.S. CPI vs. PCE price index) Monetary Policy: Data Revisions How Much Does It Matter for Monetary
Policy that Data Are Revised? Example: Feds favorite inflation measure is the Personal Consumption Expenditures Price Index Excluding Food & Energy Prices (core PCE inflation) But it has been revised substantially; similar to revisions to overall PCE inflation, as Bob Tetlow showed Monetary Policy: Data Revisions How Much Does It Matter for Monetary Policy that Data Are Revised? Charts show that instead of worrying about a substantial unwanted decline in inflation, the
Fed should have been worried about a rise in inflation Figure 1 Core PCE Inflation Rate from 1997Q1 to 2002Q1, Vintage May 2002 2.4 2.2 Inflation Rate 2.0 1.8
1.6 1.4 1.2 1.0 1997 1998 1999
2000 Date 2001 2002 Figure 3 Core PCE Inflation Rate from 1997Q1 to 2002Q1, Vintages May 2002, Dec. 2003, Aug. 2005 2.4 August 2005 2.2
Dec 2003 Inflation Rate 2.0 1.8 1.6 1.4 1.2
1.0 1997 May 2002 1998 1999 2000 Date 2001
2002 Monetary Policy: Data Revisions How Much Does It Matter for Monetary Policy that Data Are Revised? Simple regressions show that the annual revision of PCE inflation data (both overall and core) is forecastable Current Analysis How Can Real-Time Data Be Used for Current Analysis? Domenico Giannones research: extract realtime information to determine a real shock and a nominal shock, which represent
fundamental dynamics of US economy Surprising findings: surveys (especially Philadelphia Fed Business Outlook Survey) matter significantly Current Analysis Remaining issue: how helpful is nowcasting for monetary policy? Fed spends many resources on nowcasting, but policy works with a lag, so forecasting is more important Does nowcasting better help us forecast better? Or are forecasts at the policy horizon
unaffected by the nowcast? Monetary Policy: Analytical Revisions What Happens When Economists or Policymakers Revise Conceptual Variables? Output gap Natural rate of unemployment Equilibrium real interest rate Concepts are never observed, but are centerpiece of macroeconomic theory
Monetary Policy: Analytical Revisions Research: Fed overreacted to perceived output gap in 1970s, causing Great Inflation; but output gap was mismeasured Very difficult to measure output gap in real time (Simon van Norden) Different methods lead to very different output gap measures; hard to choose best method Productivity growth is revised substantially, so forecasting output gap is problematic Monetary Policy: Analytical Revisions
Policy models may change: Tetlow-Ironside (2007): changes in FRB-US model changed the story the model was telling to policymakers Model changes exacerbated by data revisions Monetary Policy: Analytical Revisions What Happens When Economists or Policymakers Revise Conceptual Variables? Key issue: end-of-sample inference for forward-looking concepts (filters) Key issue: optimal model of evolution of
analytical concepts Most work is statistical; perhaps a theoretical breakthrough is needed
You MUST have Liability Insurance to hold fundraisers and Booster Events. Protect yourself, the school, the school board . MUST include the School Board of Miami Dade County as additional insured on the policy. Tell the Insurance Agent that this...
In Primary 1 and 2, children are taught sounds through our phonics programme 'Literacy Rich'. This programme also includes the teaching of common words. Children learn to read using the Bug Club reading scheme, supplemented with library books and materials...
Performing regression on noisy data can result in models that capture noise in addition to the underlying function. Preference for smoothness can be encoded in the regression problem by adding a regularization term to the objective function. where ?≥0 is...
Choice Architecture 101. ... People tend to overweight the costs of a cab ride and underweight the full costs of having a car. A tax on energy use will have a bigger effect if the thermostat tells the user the...
El Mohan programa después de clases comenzará la primera semana de septiembre. El nuevo después de los ayudantes de la escuela . Comenzará a trabajar la semana del 18 de agosto . Se ha comprado un IPAD para cada estudiante.
Reduce DWF rate. Brings semi-knowledgeable students to you on Day 1. Fun and Engaging learning experience. More Time for: Wider Breadth or Deeper Depth of concept knowledge. Students to be: Amazed at facts, Proud of themselves, Love Learning. Forces students...