The Importance of Being Timely

Abstract

Policymakers want to know about real-time economy performance. However, closely watched macroeconomic time series produced by national statistics offices are published infrequently, with a time lag and subject to revision. Such issues create uncertainty in tracking economic developments, a by-product of which is to raise the value of business and consumer surveys. Although providing less granularity than official data series, the surveys are released in a timelier manner and are subject to little revision. Using real-time data sourced from the Deutsche Bundesbank, the OECD and the Office for National Statistics, an assessment of the role that the popular and widely used Purchasing Managers' Index (PMI) play in reducing forecasting errors in a simple 'nowcasting' framework is undertaken. The empirical exercise is conducted for five developed economies and also covers the period of the Great Recession. The conclusion is clear: timing matters.

Google's MIDAS Touch: Predicting UK Unemployment with Internet Search Data

“…The derived factors in this case were created from the first principal component from a static principal component analysis exercise similar to that used in P. Smith (). The first one (marked as F1 in the tables below) includes the eight survey‐based variables, while the second factor (F2 in the tables below), includes the survey variables plus times series for the GRI and the Google ‘root’ term, redundancy.…”

“…This could be an important advantage. As shown by P. Smith (), the marginal predictive power of an indicator can be linked to its release schedule, making it an important consideration when trying to understand its role and value to the economic forecaster.…”