The Making of National Economic Forecasts
Show Less

The Making of National Economic Forecasts

Edited by Lawrence R. Klein

This important book, prepared under the direction of Nobel Laureate Lawrence R. Klein, shows how economic forecasts are made. It explains how modern developments in information technology have made it possible to forecast frequently – at least monthly but also weekly or bi-weekly – depending upon the perceived needs of potential forecast users and also on the availability of updated material.
Buy Book in Print
Show Summary Details
You do not have access to this content

Chapter 11: Using Data and Models at Mixed Frequencies in Computation and Forecasting

Fyodor I. Kushnirsky


1 Fyodor I. Kushnirsky 1. INTRODUCTION This chapter considers the use of statistical information at mixed frequencies for estimating economic variables and forecasting. There are two types of problems involved. The first type is interpolation, i.e. the estimation of unknown variables based on related data of higher or lower frequency; this problem has always been of interest in numerical analysis, statistics and econometrics. Depending on the number and type of specified data points, some interpolation procedures are algebraic and others are statistical, resulting in obtaining an average path as an approximation. In other words, econometric estimation can be viewed as an interpolation process in a broader sense than algebraic interpolation; the generalization is caused by the fact that it is not possible to satisfy the interpolation conditions exactly at every point, and a least-squares approximation is performed by minimizing the sum of squared errors. The second type of problems, the construction of macroeconometric models at mixed frequencies and their joint use for medium- and longterm forecasting, is novel. The methodology of constructing and combining such models – high frequency, with monthly or even more frequent observations, and low frequency, with annual observations – was suggested by Klein and Kushnirsky (2005). This methodology differs from conventional forecasting techniques. To illustrate, suppose that two models at different frequencies are available in conventional medium-term forecasting. Their use will likely be arranged so that the high-frequency model is applied to the first year or two, and the low-frequency model to the rest of the period. In...

You are not authenticated to view the full text of this chapter or article.

Elgaronline requires a subscription or purchase to access the full text of books or journals. Please login through your library system or with your personal username and password on the homepage.

Non-subscribers can freely search the site, view abstracts/ extracts and download selected front matter and introductory chapters for personal use.

Your library may not have purchased all subject areas. If you are authenticated and think you should have access to this title, please contact your librarian.

Further information

or login to access all content.